© 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. 19174
    Prev
    Next
    INDEX
    Explanations

    quotation punctuation

    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
     upravo
    -0.09
    :.↵↵
    -0.09
     legitimately
    -0.09
    Unique
    -0.09
     kiddos
    -0.08
     JUST
    -0.08
    >If
    -0.08
     pricey
    -0.08
    _calc
    -0.08
    이면
    -0.08
    POSITIVE LOGITS
    ...",
    0.14
    ..."
    0.14
     something
    0.14
    ?",
    0.14
     ..."
    0.14
     (?)
    0.13
     etc
    0.13
    ?"↵
    0.13
    "?
    0.13
    ..."↵
    0.13
    Activations Density 0.107%

    No Known Activations