Daniel P. Mossing
Source-listed: Member of technical staff · Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Natural Language Autoencoders Produce Unsupervised Explanations of LLM ActivationsSaved credit: Contributor · 2026Explore people connected to this work →
- Persona Features Control Emergent MisalignmentSaved credit: Contributor · 2025Explore people connected to this work →
- Weight-sparse transformers have interpretable circuitsSaved credit: Contributor · 2025Explore people connected to this work →
- Language models can explain neurons in language modelsSaved credit: Contributor · 2023Explore people connected to this work →
- GPT-4 Technical ReportSaved credit: Contributor · 2023Explore people connected to this work →