© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108644
    Prev
    Next
    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     überhaupt
    -0.08
     uch
    -0.08
    ిశ
    -0.08
     montar
    -0.08
     xen
    -0.07
     pē
    -0.07
     kob
    -0.07
    ورس
    -0.07
    [][]
    -0.07
     ومح
    -0.07
    POSITIVE LOGITS
     conclusão
    0.11
     Thus
    0.10
     conclusión
    0.10
     voilà
    0.10
    Conclusion
    0.10
     Conclusion
    0.10
     conclusion
    0.10
    Thus
    0.10
    Таким
    0.10
    Ainsi
    0.10
    Activations Density 0.060%

    No Known Activations