About

I am currently a second-year PhD student in Purdue ECE, advised by Xiaoqian (Joy) Wang, working on LLM interpretability. I am also a co-founder of Blossoms AI and School Brain.

I earned B.A. degrees in Computer Science and Mathematics, with a minor in Philosophy, from Boston College. During my undergraduate studies, I was advised by Professors Emily Prud’hommeaux, Sergio Alvarez, Yuan Yuan, and Maira Marques Samary.

Email: zhan5982@purdue.edu

Interests

Awards & Achievements

• John McCarthy, S.J., Award for Natural Science — Boston College, May 2024. Awarded annually to one student for the best senior thesis in Natural Science.
• Neuhauser Award — Boston College Computer Science, May 2024. Awarded annually to 1–2 Computer Science students receiving exceptional recognition from faculty.
• Scholar of the College — Boston College, May 2024. Awarded to exceptional students who completed substantial, high-quality independent work under faculty supervision.

Research Projects

Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy

accepted NeurIPS 2026 · Evaluations & Datasets Track

Riteng Zhang, Xiaoqian Wang

We evaluate sparse autoencoders as systems of atomic interpretable units, examining non-redundancy, completeness, monosemanticity, dead units, and sparsity. Our framework reveals a dominant-feature failure mode: highly influential features can remain polysemantic or redundant even when conventional evaluations appear favorable.

Paper (arXiv) Code SAE checkpoints

Research visual withheld during peer review.

Research title withheld during peer review

in review ICLR 2027

Research summary and project details are withheld while the work is under review.

Title and details withheld during review.

How values may connect to internal features and concrete choices.

What Models Say vs. How They Act: Mechanistic Interpretability of Value–Action Gaps

ongoing research Mechanistic interpretability · language model behavior

We study how language models translate abstract value preferences into concrete choices. The project connects behavioral experiments with activation-level and causal evidence inside the model.

Open the Value Feature Browser

From individual interpretability methods to a reusable formal toolkit.

A Framework for Formalizing and Automating Interpretability

academic work Boston College senior thesis · 2024

My senior thesis introduced the Formalizing and Automating Interpretability Toolkit (FAI), a structured way to describe, compare, select, and implement interpretability methods.

Read the thesis (Google Drive)

Blossoms AI

I co-founded Blossoms AI in 2023 and serve as Chief AI Officer (CAIO). The next generation of education will be AI-native—inevitably—and we are building for it now.

School Brain

I am a co-founder and the Chief AI Officer (CAIO) of School Brain. We collaborate with school districts in Pennsylvania, Illinois, and Florida to build customized transportation and operations products for live workflows.

AI research assistant & reusable skills

I use Hermes as an AI research assistant and project collaborator inside Discord. It supports my research, product development, writing, and broader knowledge work. The public repository below collects the reusable skills and artifact workflows that grew out of this work.

Discord thread → project context → loaded skill → local files → QA → Thread Canvas

A persistent workspace that keeps the discussion, decisions, and linked artifacts together.

Long research threads → durable working context

Thread Canvas

Thread Canvas turns long research conversations into a durable workspace with the discussion, decisions, and artifacts in one place, so important context remains usable after the chat moves on.

Long-context continuityLinked artifactsDurable handoff

Open Thread Canvas example

Teaching

At Boston College, I served as a teaching assistant for two upper-level computer science courses. I supported Machine Learning for two semesters.