© 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. 19-RESID-POST-AA
    11. 103321
    Prev
    Next
    INDEX
    Explanations

    date and time calculations

    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
    int
    -0.08
    ruck
    -0.08
    .int
    -0.08
    -divider
    -0.08
    igen
    -0.08
    .cross
    -0.08
    ?>
    -0.08
    .Return
    -0.08
    -0.08
    ?.
    -0.08
    POSITIVE LOGITS
     treated
    0.10
     Aug
    0.09
     Monate
    0.09
     treats
    0.09
     augmented
    0.09
    treated
    0.09
     olsa
    0.08
     زم
    0.08
    _aug
    0.08
    менты
    0.08
    Activations Density 0.000%
    No Known Activations