© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30369
    Prev
    Next
    INDEX
    Explanations

    speed

    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
    很好
    -0.09
    々
    -0.08
     така
    -0.07
    sy
    -0.07
    lero
    -0.07
    ಲ್ಲಿ
    -0.07
    念
    -0.07
    有关
    -0.07
     logique
    -0.07
    ,而且
    -0.07
    POSITIVE LOGITS
    /high
    0.09
    、高
    0.08
     hitters
    0.08
     Mud
    0.08
     stuff
    0.07
    quad
    0.07
    Mud
    0.07
    /usr
    0.07
     Boo
    0.07
    Quad
    0.07
    Activations Density 0.027%

    No Known Activations