© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31423
    Prev
    Next
    INDEX
    Explanations

    World War II, Soviet 1941

    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
     팀
    -0.09
     لأنها
    -0.08
     يمثل
    -0.08
     librarians
    -0.08
     العالي
    -0.08
     प्रतिनिध
    -0.08
     مسب
    -0.08
     coconut
    -0.08
     편
    -0.08
     sederhana
    -0.08
    POSITIVE LOGITS
     Russia
    0.12
    Russia
    0.11
     USSR
    0.11
    俄罗斯
    0.11
     الروسية
    0.10
     Rusia
    0.10
     ruso
    0.10
     Stalin
    0.10
     Kazakhstan
    0.10
     Russians
    0.10
    Activations Density 0.021%

    No Known Activations