Satvik Golechha

Researcher, Independent

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

#1004 · David Chanin, James Wilken-Smith, Tomáš Dulka, Hardik Bhatnagar, Satvik Golechha, Joseph Isaac Bloom

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Among Us: A Sandbox for Measuring and Detecting Agentic Deception

#1517 Spotlight · Satvik Golechha, Adrià Garriga-Alonso

We create a sandbox for LLM-agents to elicit goal-directed open-ended strategic deception, evaluate this deceptive capability, and show that linear probes do very well at detecting it, even OOD.