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. 58861
    Prev
    Next
    INDEX
    Explanations

    ET

    np_max-act · gemini-2.0-flash

    attends to the time of an event from details describing the event.

    oai_attention-head · gpt-4oTriggered by @mlfinancebook
    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
     nonce
    -0.08
    ству
    -0.08
    ikuva
    -0.08
     wart
    -0.08
    ilte
    -0.07
     Aka
    -0.07
     grunt
    -0.07
    াতিক
    -0.07
     damaged
    -0.07
     harmony
    -0.07
    POSITIVE LOGITS
    /USD
    0.08
    .lib
    0.08
     (...
    0.08
     Podcasts
    0.07
     deras
    0.07
    下午
    0.07
    .groupby
    0.07
    /day
    0.07
     Familia
    0.07
     यस
    0.07
    Activations Density 0.004%

    No Known Activations