© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 44341
    Prev
    Next
    INDEX
    Explanations

    set

    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
     atletas
    -0.07
     repeal
    -0.07
    合集
    -0.07
     Birds
    -0.07
     prospects
    -0.07
    hatik
    -0.07
     convention
    -0.07
     tendency
    -0.07
     QUERY
    -0.06
    oked
    -0.06
    POSITIVE LOGITS
    (:,:,
    0.09
     captiv
    0.09
    [:,:,
    0.08
     sorgfält
    0.08
     디자인
    0.08
    constructed
    0.08
     제작
    0.08
     BF
    0.08
     geschickt
    0.08
     тщательно
    0.08
    Activations Density 0.009%

    No Known Activations