© 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. 18677
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    .↵
    -0.09
     કરે
    -0.09
    .↵↵
    -0.09
     mám
    -0.09
    ->
    -0.08
     바로
    -0.08
     ->
    -0.08
    ().↵
    -0.08
    <?>
    -0.08
     કરીએ
    -0.08
    POSITIVE LOGITS
     you'll
    0.15
     придется
    0.15
     devrez
    0.14
     потребуется
    0.14
     necesitar
    0.14
     consider
    0.13
    You'll
    0.13
     You'll
    0.13
     aanvullende
    0.13
     понадобится
    0.13
    Activations Density 0.018%

    No Known Activations