Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112967
    Prev
    Next
    INDEX
    Explanations

    Harsh environments

    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
     Hotels
    -0.08
     twe
    -0.08
     tickets
    -0.08
    Editors
    -0.08
    /event
    -0.08
     guestrooms
    -0.08
     retros
    -0.08
     curios
    -0.07
     textarea
    -0.07
    fires
    -0.07
    POSITIVE LOGITS
    巨大
    0.12
     daunting
    0.11
     formidable
    0.11
     dific
    0.10
     unfor
    0.10
     severely
    0.10
     overwhelming
    0.10
     huge
    0.10
     nasty
    0.10
     rampant
    0.10
    Activations Density 0.037%

    No Known Activations