© 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. 64034
    Prev
    Next
    INDEX
    Explanations

    ship

    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
    dy
    -0.09
    Exceptions
    -0.08
     CART
    -0.08
     Erinner
    -0.08
    omegran
    -0.08
     ngaj
    -0.08
     préfér
    -0.08
     sph
    -0.08
     ممت
    -0.08
    Joystick
    -0.08
    POSITIVE LOGITS
     Leonardo
    0.08
     Echo
    0.08
     nucleus
    0.08
    uzi
    0.07
     Bethlehem
    0.07
    ాయం
    0.07
     Erz
    0.07
     Ucr
    0.07
     ref
    0.07
     Abend
    0.07
    Activations Density 0.000%

    No Known Activations