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. 78558
    Prev
    Next
    INDEX
    Explanations

    coding

    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
     intrigu
    -0.09
    _you
    -0.08
     painfully
    -0.08
    73
    -0.08
     extraordinarily
    -0.08
     You've
    -0.08
    You've
    -0.08
     metaphor
    -0.08
     you've
    -0.08
    <|endoftext|>
    -0.08
    POSITIVE LOGITS
     optionally
    0.09
     Ka
    0.08
     lwa
    0.08
    Ես
    0.08
     JPanel
    0.08
     rss
    0.08
     guessed
    0.08
     People's
    0.07
    料
    0.07
     Pixabay
    0.07
    Activations Density 0.143%

    No Known Activations