← Back to People
Co-authored research on sparse autoencoders capturing neural geometry through clustering of features to understand manifold structures.
2
Mentions
2
Articles
2
Outlets
May 2026 — Jun 2026
Coverage
Companies Covered
Appears In
Articles
Most recent firstMentioned In
Referenced in coverage
Goodfire tool lets you audit and fix what your model learns before training starts
arXivpositiveJun 12, 2026
“Co-author of research on interpretability-based training and data auditing for language models”
Can SAEs Capture Neural Geometry?
Goodfire AIpositiveMay 22, 2026
“Co-authored research on sparse autoencoders capturing neural geometry through clustering of features to understand manifold structures.”