© 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. 30222
    Prev
    Next
    INDEX
    Explanations

    Deleting and box dimensions

    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
     juros
    -0.08
    bon
    -0.07
     conspiracy
    -0.07
     agrup
    -0.07
     Treat
    -0.07
    enca
    -0.07
     syst
    -0.07
    stdcall
    -0.07
     patron
    -0.07
     militaire
    -0.07
    POSITIVE LOGITS
     Geoff
    0.08
    出售
    0.08
     luggage
    0.08
     inmediatamente
    0.08
    ಿಷ
    0.08
     twilight
    0.07
    Cru
    0.07
    _lab
    0.07
    610
    0.07
    羽
    0.07
    Activations Density 0.034%

    No Known Activations