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. 60966
    Prev
    Next
    INDEX
    Explanations

    nutritional deficiencies

    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
    алы
    -0.08
     piston
    -0.08
    /Search
    -0.08
     этаж
    -0.08
     consists
    -0.07
     Ugly
    -0.07
     Elevator
    -0.07
     वाली
    -0.07
    anches
    -0.07
    logen
    -0.07
    POSITIVE LOGITS
     nutrients
    0.19
     vitamins
    0.17
     nutrientes
    0.17
     supplementation
    0.16
     Vitamins
    0.16
     витам
    0.15
     Vitamin
    0.15
     vitamin
    0.15
    Vitamin
    0.15
     nutrition
    0.14
    Activations Density 0.048%

    No Known Activations