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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30300
    Prev
    Next
    INDEX
    Explanations

    personal updates

    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
    _stmt
    -0.09
    stvu
    -0.08
    。例如
    -0.08
     allegedly
    -0.08
    内幕
    -0.08
     milag
    -0.08
    würdig
    -0.08
     вил
    -0.08
     ผู้
    -0.08
     jouw
    -0.08
    POSITIVE LOGITS
     ואני
    0.11
    昨天
    0.10
     എന്റെ
    0.10
     నా
    0.10
    昨
    0.10
     ನನ್ನ
    0.10
     করেছি
    0.10
     myself
    0.10
     என்
    0.10
     gratitude
    0.10
    Activations Density 1.031%

    No Known Activations