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. 55619
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
     Coal
    -0.09
    Coal
    -0.09
     acog
    -0.08
     coalition
    -0.08
    Hibernate
    -0.08
     firefighter
    -0.08
     coal
    -0.08
     انگی
    -0.08
     Carlisle
    -0.08
     Vox
    -0.08
    POSITIVE LOGITS
     sushi
    0.16
     Sushi
    0.12
     seafood
    0.11
     sperm
    0.10
     kao
    0.09
     Seafood
    0.09
     bamboo
    0.09
     shrimp
    0.09
     japonais
    0.08
     pescado
    0.08
    Activations Density 0.011%

    No Known Activations