© 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. 21457
    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
     Flüss
    -0.08
    络
    -0.08
     Odds
    -0.08
     Automaten
    -0.07
    หล
    -0.07
     punctuation
    -0.07
     Erotic
    -0.07
     Zugriff
    -0.07
     वायर
    -0.07
    ตี
    -0.07
    POSITIVE LOGITS
    -conscious
    0.17
    环保
    0.16
     sustainability
    0.15
     conservation
    0.15
    оохран
    0.15
     conservación
    0.14
     initiatives
    0.14
     conciencia
    0.14
    -friendly
    0.13
     stewardship
    0.13
    Activations Density 0.057%

    No Known Activations