© 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. 19-RESID-POST-AA
    11. 20379
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     purity
    -0.08
    בלי
    -0.08
    Greek
    -0.08
    純
    -0.08
    시는
    -0.08
     plaintext
    -0.07
     pretending
    -0.07
    ଚ
    -0.07
    ಶ
    -0.07
     rash
    -0.07
    POSITIVE LOGITS
    (big
    0.10
    .from
    0.09
     nnukwu
    0.09
     enormous
    0.09
     lớn
    0.09
     grande
    0.09
    .big
    0.09
    .Big
    0.09
     bigint
    0.09
     Big
    0.09
    Activations Density 0.001%

    No Known Activations