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. 30523
    Prev
    Next
    INDEX
    Explanations

    potential breakthroughs

    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
     organisator
    -0.09
    Incorrect
    -0.09
    vertheless
    -0.08
     kise
    -0.08
     angem
    -0.08
    iptables
    -0.08
    عرض
    -0.08
    atura
    -0.08
    まあ
    -0.08
    权益
    -0.08
    POSITIVE LOGITS
     revolucion
    0.11
     револю
    0.10
     rethink
    0.10
     someday
    0.09
     democrat
    0.09
     révolution
    0.09
     revolution
    0.09
     herald
    0.09
     Revolution
    0.09
     позволит
    0.09
    Activations Density 0.037%

    No Known Activations