© 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. 21970
    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
     Bege
    -0.08
     daneben
    -0.08
     src
    -0.08
     estreia
    -0.07
    ={(
    -0.07
    yyət
    -0.07
     название
    -0.07
    (src
    -0.07
     Festival
    -0.06
    src
    -0.06
    POSITIVE LOGITS
     consistency
    0.36
    Consistency
    0.34
     consistent
    0.32
     inconsist
    0.31
     inconsistent
    0.30
    consistent
    0.30
     consistente
    0.29
     incons
    0.29
     Cons
    0.27
     contradictions
    0.27
    Activations Density 0.157%

    No Known Activations