© 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 EvalsExportsinterp-engineNEWAPI 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. 63264
    Prev
    Next
    INDEX
    Explanations

    Russian language, communication

    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
    allocate
    -0.08
     Lep
    -0.08
    主义
    -0.08
    ifier
    -0.08
    IFICATE
    -0.08
    overwrite
    -0.07
     renewing
    -0.07
    佛
    -0.07
    aryana
    -0.07
    大小
    -0.07
    POSITIVE LOGITS
     avanti
    0.10
    涉
    0.09
     cabo
    0.09
     Courage
    0.08
     conduz
    0.08
     condu
    0.08
     себя
    0.08
     conduit
    0.08
     пользователя
    0.08
     conversa
    0.08
    Activations Density 0.016%

    No Known Activations