Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 60912
    Prev
    Next
    INDEX
    Explanations

    definitions and meanings

    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
     veloc
    -0.10
    Apis
    -0.09
     sipping
    -0.08
     lactose
    -0.08
     impossível
    -0.08
     protiv
    -0.08
     Heer
    -0.08
    stu
    -0.08
     obese
    -0.08
    ulik
    -0.08
    POSITIVE LOGITS
     refers
    0.09
     metaphor
    0.09
     noun
    0.08
     concept
    0.08
     detachable
    0.08
     aptly
    0.07
     trad
    0.07
    ニュー
    0.07
    テン
    0.07
     financial
    0.07
    Activations Density 0.126%

    No Known Activations