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. 49681
    Prev
    Next
    INDEX
    Explanations

    per

    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
     Lange
    -0.08
    lamak
    -0.07
    不停
    -0.07
     cherish
    -0.07
     Precious
    -0.07
     Heights
    -0.07
    arks
    -0.07
     quitte
    -0.07
    hold
    -0.07
    amul
    -0.07
    POSITIVE LOGITS
    ən
    0.09
     Elm
    0.08
    ерг
    0.08
    əl
    0.08
    ərinin
    0.07
     whipping
    0.07
    indən
    0.07
     اقدامات
    0.07
    _saved
    0.07
    __[
    0.07
    Activations Density 0.005%

    No Known Activations