© 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. 23-RESID-POST-AA
    11. 96666
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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
     katawan
    -0.07
     joj
    -0.07
    ’off
    -0.07
    DI
    -0.07
     cosmos
    -0.07
    porta
    -0.07
     invokevirtual
    -0.07
     Ingl
    -0.07
    डी
    -0.07
    Normalizer
    -0.07
    POSITIVE LOGITS
    22
    0.09
    956
    0.08
    28
    0.08
    47
    0.08
    56
    0.08
     confusion
    0.08
    <R
    0.08
     extreme
    0.07
     humor
    0.07
    ighthouse
    0.07
    Activations Density 0.012%

    No Known Activations