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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 131069
    Prev
    Next
    INDEX
    Explanations

    Iraq

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Py
    -0.13
     Swiss
    -0.13
     cocoa
    -0.12
     Cape
    -0.12
     Malagasy
    -0.12
    Py
    -0.11
     Madeira
    -0.11
     Switzerland
    -0.11
     Alpes
    -0.11
    (torch
    -0.11
    POSITIVE LOGITS
     Iraqi
    0.32
     Iraq
    0.32
     العراق
    0.30
     العراقي
    0.30
     العراقية
    0.30
     بغداد
    0.29
     عراق
    0.28
     Baghdad
    0.27
     Saddam
    0.27
     Kurdish
    0.23
    Activations Density 0.040%

    No Known Activations