© 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. 19-RESID-POST-AA
    11. 102853
    Prev
    Next
    INDEX
    Explanations

    Labor or government

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.10
     –
    -0.10
    ’,
    -0.09
     -
    -0.08
    lüsse
    -0.08
    puts
    -0.08
    <|reserved_200009|>
    -0.08
     pathways
    -0.08
     ставки
    -0.08
     +
    -0.08
    POSITIVE LOGITS
    政协
    0.09
    共中央
    0.09
     मंत्रालय
    0.08
     Protection
    0.08
    联网
    0.08
     सरकारी
    0.08
    альном
    0.08
    ологиялық
    0.08
    охран
    0.08
    讯网
    0.08
    Activations Density 0.025%

    No Known Activations