© 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. 23-RESID-POST-AA
    11. 6142
    Prev
    Next
    INDEX
    Explanations

    coding related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     formulário
    -0.08
     Emit
    -0.08
    unay
    -0.08
    opsy
    -0.08
     selecion
    -0.07
     selon
    -0.07
    fform
    -0.07
    njo
    -0.07
     Formen
    -0.07
    Rece
    -0.07
    POSITIVE LOGITS
    ate
    0.09
    ий
    0.09
     gri
    0.08
    ates
    0.08
    áth
    0.08
    _cipher
    0.08
    _gen
    0.08
    _main
    0.07
    SPI
    0.07
    ierte
    0.07
    Activations Density 0.000%

    No Known Activations