© 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. 63468
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ,opt
    -0.08
     qər
    -0.08
    ,we
    -0.07
    的时候
    -0.07
    :k
    -0.07
    -intensive
    -0.07
    =req
    -0.07
    之外
    -0.07
     ખુ
    -0.07
     kedah
    -0.07
    POSITIVE LOGITS
    OH
    0.08
     homicide
    0.08
     ран
    0.07
     Rond
    0.07
    Quote
    0.07
     probability
    0.07
    Names
    0.07
     Gesetz
    0.07
    券
    0.07
    票
    0.07
    Activations Density 0.055%

    No Known Activations