© 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. 23-RESID-POST-AA
    11. 49472
    Prev
    Next
    INDEX
    Explanations

    code configurations

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gelang
    -0.08
    icy
    -0.08
     Rating
    -0.08
     миним
    -0.08
    ibase
    -0.08
    -0.07
     siti
    -0.07
     ren
    -0.07
    steller
    -0.07
    ipt
    -0.07
    POSITIVE LOGITS
    args
    0.13
     args
    0.12
    .args
    0.11
    	args
    0.10
    Args
    0.10
    (args
    0.10
    .listen
    0.09
    Compound
    0.09
     cwd
    0.09
    _args
    0.09
    Activations Density 0.001%
    No Known Activations