© 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. 49448
    Prev
    Next
    INDEX
    Explanations

    Math/equations

    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
    senha
    -0.13
    _usuario
    -0.13
    ərbaycan
    -0.13
    _cliente
    -0.13
    _fecha
    -0.13
    _nome
    -0.13
    fecha
    -0.13
     Além
    -0.13
    _tipo
    -0.12
    now
    -0.12
    POSITIVE LOGITS
    The
    0.31
    In
    0.27
    Using
    0.27
    This
    0.27
    For
    0.26
    Also
    0.26
    Because
    0.26
    Consider
    0.26
    Potential
    0.26
    Could
    0.26
    Activations Density 1.793%

    No Known Activations