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. 48500
    Prev
    Next
    INDEX
    Explanations

    Orders

    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
    惊
    -0.08
    授
    -0.08
    丰富
    -0.08
    飞
    -0.08
    浴
    -0.08
    نع
    -0.08
     cluichí
    -0.08
    сақ
    -0.08
    دىغان
    -0.08
    ibonacci
    -0.08
    POSITIVE LOGITS
    _id
    0.12
     ID
    0.11
    _ID
    0.10
    _created
    0.10
    -ID
    0.10
    _creation
    0.10
     번호
    0.10
    -id
    0.10
     creation
    0.10
    .ID
    0.09
    Activations Density 0.047%

    No Known Activations