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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75628
    Prev
    Next
    INDEX
    Explanations

    complex writing

    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
    厂家
    -0.08
    (pol
    -0.08
     hype
    -0.07
     pol
    -0.07
    PH
    -0.07
    .king
    -0.07
    ancel
    -0.07
     ince
    -0.07
     browse
    -0.07
     circulação
    -0.07
    POSITIVE LOGITS
     upbringing
    0.12
     gratitude
    0.12
     anecdotes
    0.12
    成长
    0.11
     gelernt
    0.11
     became
    0.11
     我的
    0.11
    我的
    0.11
     cherish
    0.11
    יתי
    0.11
    Activations Density 0.042%

    No Known Activations