Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48867
    Prev
    Next
    INDEX
    Explanations

    вступ

    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
    ร้อง
    -0.08
    -0.08
     قرب
    -0.07
     என
    -0.07
     kasar
    -0.07
     Richardson
    -0.07
    бал
    -0.07
     از
    -0.07
     عضو
    -0.07
     tasks
    -0.07
    POSITIVE LOGITS
    期限
    0.11
    作用
    0.09
     동안
    0.09
     течение
    0.09
     Creat
    0.09
     Zeitraum
    0.09
     vigente
    0.09
    -lasting
    0.09
     legislation
    0.09
     berlaku
    0.09
    Activations Density 0.022%

    No Known Activations