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. 49071
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    Boost
    -0.08
    -0.08
     boost
    -0.08
    igna
    -0.08
     Boost
    -0.08
    лайды
    -0.08
     boosts
    -0.08
     boosting
    -0.07
    лаг
    -0.07
     YOU
    -0.07
    POSITIVE LOGITS
     نطاق
    0.15
    -reaching
    0.14
    范围
    0.14
    -ranging
    0.13
     alcance
    0.13
     scope
    0.13
     возможностей
    0.12
     extends
    0.12
    scope
    0.12
     beyond
    0.12
    Activations Density 0.112%

    No Known Activations