Curt Tigges
San Francisco, CA
Bio
Updated 05/18/26Curt Tigges is a mechanistic interpretability researcher whose work has focused on sparse autoencoder evaluation and circuit-level analysis of large language models. He served as science lead at Decode Research, helping direct research and design features for Neuronpedia, and later joined Goodfire AI as a researcher. He is a co-author of SAEBench and "Sparse Autoencoders Do Not Find Canonical Units of Analysis" and is widely cited for work on linear representation and sentiment circuits.
Community Signal
Updated 05/18/260Upvotes
0Downvotes
0Endorsements
No endorsements yet.
Links
Updated 05/18/26- Personal Website
- https://www.curttigges.com/
- -
- Twitter / X
- -
- LessWrong
- -
- EA Forum
- -
Grants
Updated 05/18/26No grants recorded.