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

    Neuronpedia

    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. 24990
    Prev
    Next
    INDEX
    Explanations

    Continuation and completeness

    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
    IMPORTANT
    -0.08
    >Hello
    -0.08
    алып
    -0.08
    ICY
    -0.07
    (optional
    -0.07
    شم
    -0.07
    却
    -0.07
    ాయక
    -0.07
    పడ
    -0.07
     parâ
    -0.07
    POSITIVE LOGITS
     detaill
    0.10
     상세
    0.10
     detailed
    0.10
    詳細
    0.09
    详细
    0.09
     Detailed
    0.09
    etailed
    0.08
     déta
    0.08
     detay
    0.08
    详
    0.08
    Activations Density 0.041%

    No Known Activations