© 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. 22186
    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
    ();↵↵
    -0.07
     Moroccan
    -0.07
    ;↵↵
    -0.06
    ；↵↵
    -0.06
    ;↵↵/
    -0.06
     stereotype
    -0.06
    :↵↵
    -0.06
    ));↵↵
    -0.06
    );↵↵/
    -0.06
    je
    -0.06
    POSITIVE LOGITS
     шулай
    0.13
     eveneens
    0.13
     també
    0.12
     Similarly
    0.12
     sidoo
    0.12
     ასევე
    0.12
     ankaŭ
    0.12
     također
    0.12
     таксама
    0.12
     samuti
    0.12
    Activations Density 0.074%

    No Known Activations