© 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. 11-RESID-POST-AA
    11. 114216
    Prev
    Next
    INDEX
    Explanations

    math

    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
     bring
    -0.08
     cradle
    -0.08
    shot
    -0.08
    icionar
    -0.07
     bringing
    -0.07
    不是
    -0.07
     stuff
    -0.07
     screening
    -0.07
    _machine
    -0.07
     coworkers
    -0.07
    POSITIVE LOGITS
     hinweg
    0.10
     Ony
    0.08
    Inclusive
    0.08
     Book
    0.08
    book
    0.08
    范围
    0.07
     unterschiedlich
    0.07
    涯
    0.07
    Extent
    0.07
    mits
    0.07
    Activations Density 0.031%

    No Known Activations