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. 30606
    Prev
    Next
    INDEX
    Explanations

    colors

    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
     Buddhism
    -0.08
     demeanor
    -0.08
     Vietnam
    -0.08
    edly
    -0.07
    lays
    -0.07
     socialism
    -0.07
    에서
    -0.07
    _and
    -0.07
     conducts
    -0.07
    Mart
    -0.07
    POSITIVE LOGITS
     parche
    0.09
     gewährleisten
    0.08
     сав
    0.08
     eingesetzt
    0.08
     داسې
    0.08
     ей
    0.08
     набор
    0.08
    .Cluster
    0.08
     नियुक्त
    0.08
    اره
    0.08
    Activations Density 0.005%

    No Known Activations