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. 43799
    Prev
    Next
    INDEX
    Explanations

    aerodynamics and gas dynamics

    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
     Wellness
    -0.09
     투자
    -0.09
     Workbook
    -0.09
    ลงทุน
    -0.09
     humanities
    -0.09
     scrapbook
    -0.09
    ระ
    -0.08
    -pr
    -0.08
     Worksheet
    -0.08
     wellness
    -0.08
    POSITIVE LOGITS
     airborne
    0.09
     дым
    0.09
     announ
    0.09
     aeron
    0.09
     воздуха
    0.09
     aircraft
    0.09
     congestion
    0.08
     straf
    0.08
    STATUS
    0.08
     airflow
    0.08
    Activations Density 0.005%

    No Known Activations