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. 78748
    Prev
    Next
    INDEX
    Explanations

    bill of materials

    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
     queer
    -0.09
     kios
    -0.09
     insiders
    -0.08
     zen
    -0.08
     brokers
    -0.08
     patrol
    -0.08
    锐
    -0.08
     confined
    -0.08
     Vermont
    -0.08
     painted
    -0.07
    POSITIVE LOGITS
     Ingredient
    0.13
    Ingredient
    0.12
    .ingredients
    0.12
     allergens
    0.11
    Ingredients
    0.11
     ingredient
    0.11
     Ingredients
    0.11
     ингреди
    0.11
     Zutaten
    0.10
     Meal
    0.10
    Activations Density 0.012%

    No Known Activations