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. 45093
    Prev
    Next
    INDEX
    Explanations

    /contracts

    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
     VLC
    -0.07
     Astrology
    -0.07
     Astro
    -0.07
    odd
    -0.07
     Tibet
    -0.07
     Gemini
    -0.07
    oma
    -0.07
     Analyze
    -0.07
    色色
    -0.07
     Pent
    -0.07
    POSITIVE LOGITS
    IERC
    0.09
    ισ
    0.09
     IERC
    0.08
    Upgradeable
    0.08
     BOX
    0.08
    Stamped
    0.08
    Authenticated
    0.08
    ப
    0.08
    ماس
    0.08
     கவ
    0.08
    Activations Density 0.001%

    No Known Activations