© 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. 18836
    Prev
    Next
    INDEX
    Explanations

    upper bounds

    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
    ormais
    -0.07
    дет
    -0.07
     сделал
    -0.07
     нович
    -0.07
     впервые
    -0.07
     lancer
    -0.07
    Zero
    -0.07
     рекомендации
    -0.07
     нын
    -0.07
     natus
    -0.07
    POSITIVE LOGITS
     upper
    0.23
    upper
    0.20
    Upper
    0.20
     Upper
    0.20
    _upper
    0.19
    -upper
    0.16
     oberen
    0.16
    .upper
    0.14
     xmax
    0.14
     maximum
    0.14
    Activations Density 0.063%

    No Known Activations