Zach Maas
- AI Safety Researcher ⋅ PhD in ML for computational biology
Hi! I’m Zach. I’m currently an AI safety researcher at AE Studio. I’m also wrapping up some independent work on SAE representation geometry on a Coefficient Giving TAIS grant. My independent work focuses on approaches to better understand structure in learned sparse bases for interpretability. During my PhD, I worked on trying to understand interpretability in biological models where we don’t have the same semantic grounding that’s present in language.
Boulder, CO ⋅ hey@zachmaas.com ⋅ @zmaas ⋅ zach-maas
News
- 2026/09: Started full-time at AE Studio
- 2026/07: Presented spotlight in the Mechanistic Interpretability Workshop at ICML 2026
- 2026/01: Started Coefficient Giving TAIS grant
- 2025/05: Completed my PhD!
Highlighted Work:
- Conditional Dependence Structure in Sparse Autoencoder Features: ICML Mech Interp Workshop 2026 spotlight. Dependence graph structure in SAEs
- Graph Structure Compresses Contrastive Neuron Steering Targets: Can we steer LLM behavior using only MLPs + structured dependence?
- Preliminary Results on Graph SAEs: Building dependence graphs off of SAEs to understand their structure
- Research Notes: Sequence to Read Models: Notes on how to build (and not build) sequence-to-read genomic models