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

    Neuronpedia

    Jacobian LensNEW
    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. 63599
    Prev
    Next
    INDEX
    Explanations

    Code with time intervals

    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
     arguments
    -0.09
    arguments
    -0.08
     straightforward
    -0.08
     repris
    -0.07
    针对
    -0.07
    Arguments
    -0.07
     argumentos
    -0.07
    明确
    -0.07
    \Facades
    -0.07
    _args
    -0.07
    POSITIVE LOGITS
    .random
    0.28
    随机
    0.28
     randomly
    0.27
     random
    0.27
     Random
    0.26
    Random
    0.26
    .Random
    0.26
    _random
    0.26
    random
    0.25
    =random
    0.25
    Activations Density 0.041%

    No Known Activations