© 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. 96262
    Prev
    Next
    INDEX
    Explanations

    Regular expressions

    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
     стране
    -0.08
    opyright
    -0.08
     उन्ह
    -0.08
     kosa
    -0.08
    empty
    -0.08
    anio
    -0.08
    readonly
    -0.07
    gree
    -0.07
    delegate
    -0.07
    ileno
    -0.07
    POSITIVE LOGITS
    (([
    0.12
    W
    0.12
    ]\
    0.11
    )$
    0.11
    (|
    0.11
    [[
    0.10
    s
    0.10
    stest
    0.10
    )\
    0.10
    ((
    0.10
    Activations Density 0.001%

    No Known Activations