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. 394
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
    ોજન
    -0.07
     operational
    -0.07
     pretend
    -0.07
     suicidal
    -0.07
    ೇಕ
    -0.07
     redirects
    -0.07
     pret
    -0.07
     яр
    -0.07
     protection
    -0.07
     বৰ
    -0.07
    POSITIVE LOGITS
     consecut
    0.10
    Sorted
    0.10
    ,next
    0.09
    ,第
    0.09
     Sorted
    0.09
    .next
    0.09
    nth
    0.09
    _NEXT
    0.09
     Iterator
    0.09
    (next
    0.09
    Activations Density 0.021%

    No Known Activations