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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 408
    Prev
    Next
    INDEX
    Explanations

    Cyrillic "В"

    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
     explored
    -0.08
     exploration
    -0.08
    惊
    -0.08
    幸
    -0.08
     explorer
    -0.08
     службу
    -0.07
     Exploration
    -0.07
    Expl
    -0.07
    Explore
    -0.07
    _CLEAR
    -0.07
    POSITIVE LOGITS
     الشركات
    0.08
     undergoing
    0.08
     conversions
    0.08
     valor
    0.07
     portfolio
    0.07
    .educ
    0.07
     toepassingen
    0.07
    ould
    0.07
    ،↵
    0.07
    emás
    0.07
    Activations Density 0.000%

    No Known Activations