© 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. 97630
    Prev
    Next
    INDEX
    Explanations

    musical chord notation

    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
     הראשון
    -0.10
     {})↵
    -0.10
    есінің
    -0.10
     []↵
    -0.10
    есін
    -0.10
    יברס
    -0.10
     ")[
    -0.09
     [])↵
    -0.09
     "))↵
    -0.09
     שבו
    -0.09
    POSITIVE LOGITS
    maj
    0.16
    �
    0.15
    dim
    0.15
    sus
    0.15
    7
    0.15
    add
    0.14
    #m
    0.14
    /F
    0.13
    m
    0.13
    Maj
    0.13
    Activations Density 0.008%

    No Known Activations