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. 11608
    Prev
    Next
    INDEX
    Explanations

    Image processing / OCR

    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
    照
    -0.08
     fandom
    -0.08
     ಭೇಟ
    -0.08
    Phi
    -0.07
    本
    -0.07
    是真的吗
    -0.07
     crescita
    -0.07
    chedules
    -0.07
     replacements
    -0.07
    -liked
    -0.07
    POSITIVE LOGITS
    �
    0.08
     Россий
    0.08
     maks
    0.07
     enfoque
    0.07
     kalk
    0.07
     يم
    0.07
     режиме
    0.07
     Wichtig
    0.07
    োঁ
    0.07
     ভাবে
    0.07
    Activations Density 0.001%

    No Known Activations