© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19178
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :↵
    -0.16
    ↵
    -0.13
    ：↵
    -0.12
     **
    -0.12
    .↵
    -0.12
    :
    -0.11
    :↵↵
    -0.11
    :
↵
    -0.10
    ;↵
    -0.10
     :↵
    -0.10
    POSITIVE LOGITS
    Because
    0.23
    The
    0.22
    It's
    0.22
    Since
    0.22
    Given
    0.22
    There
    0.21
    Although
    0.20
    Using
    0.20
     There
    0.20
    It
    0.20
    Activations Density 0.055%

    No Known Activations