© 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. 19-RESID-POST-AA
    11. 102404
    Prev
    Next
    INDEX
    Explanations

    CUDA and GPU

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     genealog
    -0.13
     Whois
    -0.11
     Tante
    -0.11
     genealogy
    -0.11
     Winchester
    -0.10
     archa
    -0.10
     wedding
    -0.09
     literary
    -0.09
     Wedding
    -0.09
     विवाह
    -0.09
    POSITIVE LOGITS
     CUDA
    0.27
    CUDA
    0.27
    _gpu
    0.25
    cuda
    0.25
     GPU
    0.25
    _cuda
    0.25
     cuda
    0.25
    .cuda
    0.25
     gpu
    0.25
    _GPU
    0.23
    Activations Density 0.013%

    No Known Activations