© 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. 22459
    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
     القدرة
    -0.09
     функциони
    -0.09
     residência
    -0.08
     منزل
    -0.08
     الرياض
    -0.08
    家庭
    -0.08
    cstdlib
    -0.08
     عملکرد
    -0.08
    äss
    -0.08
     vuestro
    -0.08
    POSITIVE LOGITS
    (PDO
    0.08
     truck
    0.08
    (step
    0.08
    Long
    0.07
    $db
    0.07
     largos
    0.07
     gigs
    0.07
     largas
    0.07
     titt
    0.07
    truck
    0.07
    Activations Density 0.003%

    No Known Activations