© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 112555
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    итай
    -0.08
    -0.08
    -Apr
    -0.08
    ोग
    -0.08
    mei
    -0.08
     choir
    -0.08
    _Common
    -0.07
     Tribe
    -0.07
    र्जा
    -0.07
     portas
    -0.07
    POSITIVE LOGITS
     Coorden
    0.09
     coorden
    0.09
     متعددة
    0.09
     Coord
    0.08
     Kelvin
    0.08
     দুটি
    0.08
     Cartesian
    0.08
     গু
    0.08
     Coordinate
    0.08
    二维
    0.08
    Activations Density 0.037%
    No Known Activations