© 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. 78788
    Prev
    Next
    INDEX
    Explanations

    code labels and text

    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
    歴
    -0.08
     cherchez
    -0.07
    _FL
    -0.07
     maternal
    -0.07
    তিনি
    -0.07
     besar
    -0.07
     Danielle
    -0.07
     dramat
    -0.07
    Drama
    -0.07
     prendre
    -0.07
    POSITIVE LOGITS
     ভিত
    0.15
    Inside
    0.14
     внутри
    0.14
     inside
    0.14
    _inside
    0.14
     Inside
    0.13
     داخل
    0.13
    inside
    0.12
     अंदर
    0.11
     dedans
    0.11
    Activations Density 0.014%

    No Known Activations