© 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. 22275
    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
     or
    -0.15
    或
    -0.14
    或者
    -0.14
     किंवा
    -0.13
     oder
    -0.13
    また
    -0.13
    거나
    -0.13
     alebo
    -0.12
     either
    -0.12
     또는
    -0.12
    POSITIVE LOGITS
    –
    0.09
     იყვნენ
    0.09
    -ს
    0.09
    -მ
    0.09
     деді
    0.09
    დნენ
    0.09
     uitsluitend
    0.09
    ­↵↵
    0.09
    -ე
    0.09
    óirí
    0.09
    Activations Density 0.005%

    No Known Activations