© 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. 26376
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     μεγαλύτε
    -0.09
     Gal
    -0.08
    Archives
    -0.08
     odst
    -0.08
     Maestro
    -0.08
    .IDENTITY
    -0.08
     Уз
    -0.08
     michael
    -0.08
     واضحة
    -0.08
    λια
    -0.07
    POSITIVE LOGITS
     pess
    0.08
    ünde
    0.08
     sip
    0.08
    	wp
    0.07
    uthe
    0.07
     tempted
    0.07
    sip
    0.07
    enthe
    0.07
    emp
    0.07
     ses
    0.07
    Activations Density 0.192%

    No Known Activations