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. 44239
    Prev
    Next
    INDEX
    Explanations

    ingredients

    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
    -lived
    -0.10
     correspondence
    -0.09
    择
    -0.09
     IRQ
    -0.08
    .Visual
    -0.08
    Rent
    -0.08
    迁
    -0.08
    ONU
    -0.08
     inconvenient
    -0.08
     rent
    -0.08
    POSITIVE LOGITS
     additives
    0.12
     ingredients
    0.12
     composition
    0.12
     ingredientes
    0.12
    ingredients
    0.12
     ингреди
    0.12
     ingrédients
    0.11
    组成
    0.11
     ingrediënten
    0.11
     Composition
    0.11
    Activations Density 0.089%

    No Known Activations