© 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. 70654
    Prev
    Next
    INDEX
    Explanations

    "<"

    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
     Uf
    -0.08
    钻
    -0.08
    unika
    -0.08
     uf
    -0.08
     श
    -0.07
     Extra
    -0.07
    .extra
    -0.07
     Bauer
    -0.07
    -extra
    -0.07
    _EXTRA
    -0.07
    POSITIVE LOGITS
    hm
    0.08
     ಸ್ಥಳ
    0.07
     conceived
    0.07
    501
    0.07
    kms
    0.07
    KS
    0.07
    지고
    0.07
    ोस
    0.07
    101
    0.07
    εργ
    0.07
    Activations Density 0.001%

    No Known Activations