© 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. 108443
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Roles
    -0.08
    baden
    -0.08
    kino
    -0.07
     transición
    -0.07
     রব
    -0.07
    .minimum
    -0.07
    \Input
    -0.07
    ONT
    -0.07
    _Widget
    -0.07
    certificate
    -0.07
    POSITIVE LOGITS
    	io
    0.08
     آور
    0.08
     io
    0.08
     com
    0.08
     imu
    0.07
    ullu
    0.07
    io
    0.07
     Chees
    0.07
    -com
    0.07
    iox
    0.07
    Activations Density 0.033%

    No Known Activations