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. 56055
    Prev
    Next
    INDEX
    Explanations

    clock synchronization

    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
     newbie
    -0.08
     scored
    -0.08
     taxed
    -0.08
     taxpayer
    -0.08
     gedaan
    -0.07
    ひ
    -0.07
    ipat
    -0.07
     했
    -0.07
    途
    -0.07
    _tax
    -0.07
    POSITIVE LOGITS
     synchronization
    0.17
     Synchron
    0.16
    Synchronization
    0.16
     synchron
    0.14
     synchronize
    0.14
    Synchron
    0.14
    (sync
    0.14
    ynchron
    0.14
     synchronized
    0.13
     Sync
    0.13
    Activations Density 0.007%

    No Known Activations