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. 11640
    Prev
    Next
    INDEX
    Explanations

    article

    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
    -string
    -0.09
    >")↵
    -0.08
    >)↵
    -0.08
     Verein
    -0.08
     tentative
    -0.08
    -even
    -0.08
     »
    -0.08
     truc
    -0.07
    >())↵
    -0.07
    ")]↵
    -0.07
    POSITIVE LOGITS
     counterparts
    0.10
     उपलब्ध
    0.09
     duplicates
    0.08
     имеется
    0.08
     имеются
    0.08
     tersedia
    0.08
    ครบ
    0.08
     counterpart
    0.08
     collectible
    0.07
     copies
    0.07
    Activations Density 0.013%

    No Known Activations