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. 54332
    Prev
    Next
    INDEX
    Explanations

    question answering in history

    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
    秒
    -0.09
    Preference
    -0.09
     unhas
    -0.08
     秒
    -0.08
    Preferences
    -0.08
     preferences
    -0.08
    Preferred
    -0.08
     Recommended
    -0.08
     hjá
    -0.08
     safest
    -0.08
    POSITIVE LOGITS
     당시
    0.16
    时期
    0.14
     WWII
    0.14
     historians
    0.13
     geopolitical
    0.13
     damal
    0.12
     damals
    0.12
     medieval
    0.12
    政治
    0.12
     historian
    0.12
    Activations Density 0.179%

    No Known Activations