Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 113998
    Prev
    Next
    INDEX
    Explanations

    Ideal gas law

    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
    .an
    -0.08
    حال
    -0.08
     DHA
    -0.07
     رشته
    -0.07
     hairs
    -0.07
    وقة
    -0.07
     ఇ
    -0.07
     feathers
    -0.07
     Mü
    -0.07
     achter
    -0.07
    POSITIVE LOGITS
     ноут
    0.08
     закона
    0.08
     измен
    0.08
    (statement
    0.08
     изменения
    0.08
    (cliente
    0.08
     계약
    0.08
    (Simple
    0.08
    :',↵
    0.08
    (simple
    0.08
    Activations Density 0.002%

    No Known Activations