© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75585
    Prev
    Next
    INDEX
    Explanations

    geology and ancient studies

    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
    -0.08
     amt
    -0.08
    قلاب
    -0.07
     sentencia
    -0.07
     treg
    -0.07
     Rotten
    -0.07
     Citrus
    -0.07
    igten
    -0.07
    찮
    -0.07
    ruta
    -0.07
    POSITIVE LOGITS
     litter
    0.08
     dens
    0.08
    BI
    0.08
    �
    0.07
     кос
    0.07
     لت
    0.07
     olsun
    0.07
    /pi
    0.07
     tark
    0.07
    logs
    0.07
    Activations Density 0.002%

    No Known Activations