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. 111582
    Prev
    Next
    INDEX
    Explanations

    video

    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
    mur
    -0.08
     sediments
    -0.08
     buf
    -0.08
     remnants
    -0.08
     ld
    -0.08
     miscellaneous
    -0.07
    inet
    -0.07
     dwell
    -0.07
    eker
    -0.07
     translations
    -0.07
    POSITIVE LOGITS
    -enabled
    0.10
     échange
    0.09
    -cap
    0.08
    .imwrite
    0.08
    交流
    0.08
     আদ
    0.08
     ಕ
    0.08
    -family
    0.08
    ග
    0.08
    -spe
    0.08
    Activations Density 0.009%

    No Known Activations