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. 65182
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    -dimensional
    -0.08
     میں
    -0.08
     empfind
    -0.08
     गीत
    -0.08
    τικά
    -0.08
     expenditures
    -0.08
    ./
    -0.07
    etailed
    -0.07
     निध
    -0.07
     proprietary
    -0.07
    POSITIVE LOGITS
     সোমবার
    0.12
     weekday
    0.11
     মঙ্গলবার
    0.11
    Week
    0.11
     weekdays
    0.10
     শনিবার
    0.10
    星期
    0.10
     Mondays
    0.10
    Weekly
    0.10
    weekday
    0.10
    Activations Density 0.045%

    No Known Activations