© 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. 111061
    Prev
    Next
    INDEX
    Explanations

    data tables or lists

    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
    Hell
    -0.09
    Workbench
    -0.09
     Beard
    -0.08
    �
    -0.08
     rm
    -0.08
    Tiny
    -0.08
    (ap
    -0.08
    Cursor
    -0.08
    Copper
    -0.08
     madness
    -0.07
    POSITIVE LOGITS
     smartphones
    0.09
    riana
    0.08
     ...
↵
    0.08
     ತಮ್ಮ
    0.08
     связано
    0.08
     ...↵↵
    0.08
     regards
    0.07
     অধিক
    0.07
     кү
    0.07
     विव
    0.07
    Activations Density 0.010%

    No Known Activations