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. 119260
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
     Bean
    -0.09
    .Bean
    -0.09
    .bean
    -0.09
     Rossi
    -0.09
    	bean
    -0.08
     hikari
    -0.08
     bean
    -0.08
     cruz
    -0.08
     podnik
    -0.08
     GEM
    -0.08
    POSITIVE LOGITS
     approxim
    0.10
     numeric
    0.09
     approximation
    0.09
    Ζ
    0.08
    Ε
    0.08
     अनुमान
    0.08
     numerical
    0.08
     अंद
    0.08
    Из
    0.08
     opc
    0.08
    Activations Density 0.037%

    No Known Activations