© 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. 99362
    Prev
    Next
    INDEX
    Explanations

    Nest

    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
    轉
    -0.08
     interno
    -0.08
    ────────
    -0.08
    覽
    -0.07
    .pe
    -0.07
    添加
    -0.07
     breaks
    -0.07
    \a
    -0.07
    拆
    -0.07
    lossen
    -0.07
    POSITIVE LOGITS
     poderia
    0.08
     Clayton
    0.08
     Pode
    0.07
     زه
    0.07
     Tagged
    0.07
     voldoen
    0.07
     zah
    0.07
     Stro
    0.07
    Sta
    0.07
     Masse
    0.07
    Activations Density 0.017%

    No Known Activations