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. 60728
    Prev
    Next
    INDEX
    Explanations

    nutrition recommendations

    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
    (core
    -0.08
    素材
    -0.08
     suitcase
    -0.08
    אל
    -0.07
    汇
    -0.07
    Quadr
    -0.07
     וס
    -0.07
    .find
    -0.07
     and
    -0.07
     אשר
    -0.07
    POSITIVE LOGITS
     sedent
    0.13
     ಆರೋಗ್ಯ
    0.11
     pregnant
    0.10
     ആരോഗ്യ
    0.10
     건강
    0.10
    ظمة
    0.10
     Dietary
    0.10
     lifestyles
    0.10
     females
    0.10
     女性
    0.10
    Activations Density 0.018%

    No Known Activations