© 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. 78409
    Prev
    Next
    INDEX
    Explanations

    period

    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
     deui
    -0.08
     insecurity
    -0.08
     todavía
    -0.08
     precisamente
    -0.08
    Episodes
    -0.08
     episod
    -0.08
    _DLL
    -0.08
     cravings
    -0.07
     chcete
    -0.07
     gerçekten
    -0.07
    POSITIVE LOGITS
     Conclusion
    0.09
     circumvent
    0.08
    Conclusion
    0.08
     licence
    0.07
     Thus
    0.07
    inin
    0.07
    Assim
    0.07
     cement
    0.07
     Bob
    0.07
     Rath
    0.07
    Activations Density 0.068%

    No Known Activations