© 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. 71189
    Prev
    Next
    INDEX
    Explanations

    brain studies

    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
    osition
    -0.09
    verb
    -0.08
    ,set
    -0.08
    ,&
    -0.08
    ={<
    -0.08
     stod
    -0.08
    aution
    -0.08
    essian
    -0.08
    redit
    -0.08
    AUTO
    -0.08
    POSITIVE LOGITS
     διάρκ
    0.10
    宅
    0.09
     ದಿನ
    0.09
     berjalan
    0.09
    按摩
    0.08
     Ramadan
    0.08
    隔
    0.08
     दिन
    0.08
    一天
    0.08
     실시
    0.08
    Activations Density 0.007%

    No Known Activations