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. 102660
    Prev
    Next
    INDEX
    Explanations

    Measurements and ages

    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
    베
    -0.08
     erschien
    -0.08
    Exports
    -0.08
    auftrag
    -0.08
    uek
    -0.07
     craw
    -0.07
     prid
    -0.07
     recruitment
    -0.07
     bede
    -0.07
     عرضه
    -0.07
    POSITIVE LOGITS
     stature
    0.09
     salsa
    0.08
     நிலையில்
    0.08
     lyrical
    0.08
    oso
    0.08
    人士
    0.08
     говорить
    0.07
     singing
    0.07
    ego
    0.07
     dignity
    0.07
    Activations Density 0.004%

    No Known Activations