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. 12680
    Prev
    Next
    INDEX
    Explanations

    code

    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
     scientific
    -0.08
    tracted
    -0.08
     (
    -0.08
     a
    -0.08
    Assistant
    -0.07
    m
    -0.07
    Supplier
    -0.07
    先生
    -0.07
    Provider
    -0.07
     науч
    -0.07
    POSITIVE LOGITS
    .|
    0.10
     까
    0.08
     Adidas
    0.08
     konse
    0.08
    -क
    0.08
     stanje
    0.08
    -ক
    0.08
     adjectives
    0.08
    -|
    0.08
     kill
    0.08
    Activations Density 0.000%

    No Known Activations