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. 12871
    Prev
    Next
    INDEX
    Explanations

    well

    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
    nesium
    -0.08
    opter
    -0.08
    chem
    -0.07
     borrowing
    -0.07
    (pipe
    -0.07
    ホ
    -0.07
    相信
    -0.07
    ht
    -0.07
    emet
    -0.07
    仪
    -0.07
    POSITIVE LOGITS
     oddly
    0.09
     accomplishment
    0.09
     workplace
    0.09
     Handle
    0.08
     ADE
    0.08
     begun
    0.08
     discharged
    0.08
     완료
    0.08
     praesent
    0.08
    Handled
    0.08
    Activations Density 0.004%

    No Known Activations