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. 58414
    Prev
    Next
    INDEX
    Explanations

    $

    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
    .Long
    -0.09
    ริ
    -0.09
     Volume
    -0.08
    בריק
    -0.08
     rerum
    -0.07
     hanze
    -0.07
    inkles
    -0.07
     grens
    -0.07
    .Volume
    -0.07
     gbas
    -0.07
    POSITIVE LOGITS
     đơn
    0.08
     refundable
    0.08
     Прост
    0.08
     площад
    0.08
     એલ
    0.08
     taxable
    0.08
     honderden
    0.07
     مراق
    0.07
     Tampa
    0.07
     cientos
    0.07
    Activations Density 0.011%

    No Known Activations