© 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. 21854
    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
     обзор
    -0.09
    ädchen
    -0.08
     često
    -0.08
     большинство
    -0.08
     常
    -0.08
    requently
    -0.07
     otáz
    -0.07
     большинстве
    -0.07
     спраш
    -0.07
     pitanja
    -0.07
    POSITIVE LOGITS
     inconvenience
    0.23
     inconven
    0.20
     damages
    0.18
     ущер
    0.18
     નુક
    0.18
     suffered
    0.18
     harmed
    0.18
     daños
    0.17
    损
    0.17
     피해
    0.17
    Activations Density 0.034%

    No Known Activations