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

    Neuronpedia

    APICircuit 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. 12968
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Fund
    -0.08
     various
    -0.08
     of
    -0.07
    Contributor
    -0.07
     even
    -0.07
     Lon
    -0.07
    Threshold
    -0.07
     run
    -0.07
    Device
    -0.06
     instrument
    -0.06
    POSITIVE LOGITS
    �
    0.10
    лімет
    0.09
     badkamer
    0.09
    จีน
    0.08
    无遮挡
    0.08
    ละเอียด
    0.08
    اصيل
    0.08
     histori
    0.08
     حول
    0.08
     baisse
    0.08
    Activations Density 0.009%

    No Known Activations