© 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. 21906
    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
     olduk
    -0.08
     həy
    -0.08
     entweder
    -0.08
    ыза
    -0.08
     kritisch
    -0.08
    ştir
    -0.08
     hadlay
    -0.08
     pity
    -0.08
    ураль
    -0.08
    istika
    -0.07
    POSITIVE LOGITS
    posium
    0.12
    deith
    0.11
    မန္မာ
    0.11
    raeg
    0.10
    nergy
    0.10
    énées
    0.10
    THON
    0.10
    gja
    0.09
    မိဳ
    0.09
    lical
    0.09
    Activations Density 0.158%

    No Known Activations