© 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. 111150
    Prev
    Next
    INDEX
    Explanations

    code, functions

    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
     approaching
    -0.07
    expect
    -0.07
    .Expect
    -0.07
     رز
    -0.07
    ơ
    -0.07
     geschaffen
    -0.07
     pribli
    -0.07
     eset
    -0.07
    iak
    -0.07
    olone
    -0.07
    POSITIVE LOGITS
     triggered
    0.11
    .trigger
    0.10
    _trigger
    0.09
    Triggered
    0.09
     कार्र
    0.09
     Trigger
    0.09
     выполнение
    0.09
     действий
    0.08
     triggering
    0.08
     triggers
    0.08
    Activations Density 0.021%

    No Known Activations