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. 117477
    Prev
    Next
    INDEX
    Explanations

    mention

    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
     아무
    -0.08
    ')[
    -0.08
    _gui
    -0.08
     완
    -0.07
     이상
    -0.07
    /free
    -0.07
    _busy
    -0.07
    いや
    -0.07
     Ultimately
    -0.07
     정치
    -0.07
    POSITIVE LOGITS
    注明
    0.11
     explicitly
    0.10
     mention
    0.08
     perme
    0.08
     discuss
    0.08
    ೇಳ
    0.08
     اشاره
    0.08
     include
    0.08
    蜂
    0.08
     disclaim
    0.07
    Activations Density 0.060%

    No Known Activations