© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18713
    Prev
    Next
    INDEX
    Explanations

    every

    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
     the
    -0.12
    	the
    -0.10
     specific
    -0.09
     concentrations
    -0.09
     Specific
    -0.09
    the
    -0.09
    .Brand
    -0.09
     inhibitors
    -0.09
    最准
    -0.09
     spécifiques
    -0.09
    POSITIVE LOGITS
     입력
    0.10
    _input
    0.10
     input
    0.10
    _request
    0.09
     query
    0.09
     processamento
    0.09
     admission
    0.08
     request
    0.08
    <|start|>
    0.08
     solicitud
    0.08
    Activations Density 0.073%

    No Known Activations