© 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. 19075
    Prev
    Next
    INDEX
    Explanations

    increasing or decreasing

    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
    iteľ
    -0.08
    gym
    -0.08
    .zip
    -0.08
     zip
    -0.08
     anonym
    -0.08
    zip
    -0.08
    snake
    -0.08
    包
    -0.08
    Singapore
    -0.07
     cartons
    -0.07
    POSITIVE LOGITS
     greater
    0.12
     увеличение
    0.12
     مقارنة
    0.12
     increasing
    0.12
     decreasing
    0.12
     større
    0.11
     increased
    0.11
     comparación
    0.11
     comparação
    0.11
     Increasing
    0.11
    Activations Density 0.023%

    No Known Activations