© 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. 94664
    Prev
    Next
    INDEX
    Explanations

    wadd

    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
    -mentioned
    -0.08
    秘书
    -0.08
     என
    -0.08
     الأمنية
    -0.08
    時計
    -0.08
     содержания
    -0.07
     Secretaría
    -0.07
    Resident
    -0.07
     образования
    -0.07
    одейств
    -0.07
    POSITIVE LOGITS
    来到
    0.11
     pav
    0.09
     arrived
    0.08
     feas
    0.08
     পথে
    0.08
     paw
    0.08
     stumbled
    0.07
     anx
    0.07
     atrás
    0.07
     osteoporosis
    0.07
    Activations Density 0.014%

    No Known Activations