Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43747
    Prev
    Next
    INDEX
    Explanations

    chimes

    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
    征
    -0.09
    ありません
    -0.08
     entren
    -0.07
     overseeing
    -0.07
     arred
    -0.07
     keiner
    -0.07
     موجود
    -0.07
    ERT
    -0.07
     없습니다
    -0.07
    _pc
    -0.07
    POSITIVE LOGITS
    usuf
    0.08
     lavender
    0.08
     Chiang
    0.08
     Hasan
    0.07
    NOTE
    0.07
     stochastic
    0.07
     Agus
    0.07
    乌
    0.07
     tropical
    0.07
     chrysanthemums
    0.07
    Activations Density 0.001%

    No Known Activations