© 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. 19023
    Prev
    Next
    INDEX
    Explanations

    contractions and 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
    ರ್ಶನ
    -0.09
    /[
    -0.08
    NAME
    -0.08
    ([
    -0.08
     presença
    -0.08
    (blob
    -0.08
    -0.08
    -0.08
    =[
    -0.08
     IDENT
    -0.08
    POSITIVE LOGITS
     doesn't
    0.10
     інш
    0.10
    can't
    0.10
    They're
    0.10
    don't
    0.10
    Don't
    0.09
     XNUMX
    0.09
     they're
    0.09
    'clock
    0.09
     they'll
    0.09
    Activations Density 0.003%

    No Known Activations