© 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. 110959
    Prev
    Next
    INDEX
    Explanations

    the

    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
     impetus
    -0.07
    fford
    -0.07
    满
    -0.07
     boyunca
    -0.07
    inks
    -0.07
     creciente
    -0.07
    construct
    -0.07
     designated
    -0.07
     CS
    -0.07
     Bloom
    -0.07
    POSITIVE LOGITS
    .Api
    0.08
    Maar
    0.08
    .Firebase
    0.08
     mutta
    0.08
    >A
    0.07
    DAR
    0.07
     contests
    0.07
    .Country
    0.07
     мен
    0.07
    мен
    0.07
    Activations Density 0.000%

    No Known Activations