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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 113309
    Prev
    Next
    INDEX
    Explanations

    Use

    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
     борьбы
    -0.08
     Einkauf
    -0.08
     Kooperation
    -0.08
     Alltag
    -0.07
     Gas
    -0.07
    (Generic
    -0.07
     торговли
    -0.07
     ayr
    -0.07
     tay
    -0.07
    ボ
    -0.07
    POSITIVE LOGITS
    ದಲ್ಲ
    0.08
    Worldwide
    0.08
    Rome
    0.07
     worldwide
    0.07
    ذك
    0.07
    ónde
    0.07
     Heming
    0.07
    ilece
    0.07
    Follow
    0.07
    HTTPS
    0.07
    Activations Density 0.003%

    No Known Activations