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. 58712
    Prev
    Next
    INDEX
    Explanations

    web scraping/automation

    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
     centrifugal
    -0.09
    Borrow
    -0.08
     Jordan
    -0.07
    Jordan
    -0.07
    borrow
    -0.07
    érit
    -0.07
    centric
    -0.07
     Jacksonville
    -0.07
     Polyn
    -0.07
    赋
    -0.07
    POSITIVE LOGITS
     duo
    0.08
     getaway
    0.08
     surveillance
    0.08
    .sec
    0.08
     Surveillance
    0.08
     descarg
    0.08
     escl
    0.08
     MA
    0.08
     Schol
    0.07
     sek
    0.07
    Activations Density 0.001%

    No Known Activations