© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31150
    Prev
    Next
    INDEX
    Explanations

    Raspberry Pi

    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
     χρόνια
    -0.08
     outright
    -0.08
     пур
    -0.08
     parentheses
    -0.08
    almost
    -0.07
     nearly
    -0.07
    资本
    -0.07
     divine
    -0.07
     jut
    -0.07
    ात्मक
    -0.07
    POSITIVE LOGITS
    -powered
    0.09
     Skull
    0.08
     Ordem
    0.08
     Pico
    0.08
     hamburger
    0.08
     Assistant
    0.07
     footprint
    0.07
     Accent
    0.07
     compagnon
    0.07
     പോല
    0.07
    Activations Density 0.003%

    No Known Activations