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. 43995
    Prev
    Next
    INDEX
    Explanations

    quizzes or self-assessment

    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
     Neon
    -0.09
     resurrect
    -0.08
     Zuh
    -0.08
     depositing
    -0.08
     interception
    -0.08
    clang
    -0.08
     succeeded
    -0.08
     condemned
    -0.08
     neon
    -0.08
    辉
    -0.08
    POSITIVE LOGITS
     intros
    0.15
     questionnaires
    0.14
     questionnaire
    0.14
    _self
    0.13
     diagnóstico
    0.11
     oefeningen
    0.11
     Questionnaire
    0.11
    Self
    0.11
     Self
    0.11
     feelings
    0.11
    Activations Density 0.055%

    No Known Activations