© 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. 22649
    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
     ځل
    -0.09
     ಮಾತ
    -0.08
     جڏهن
    -0.08
     jeden
    -0.08
     reuse
    -0.08
     marchés
    -0.08
     ಜಯ
    -0.08
     adult
    -0.08
     adults
    -0.08
     رجل
    -0.08
    POSITIVE LOGITS
     perpendicular
    0.17
     orth
    0.16
    Orth
    0.15
     Orth
    0.15
    orth
    0.14
     орт
    0.13
     ort
    0.12
     perp
    0.11
     transverse
    0.11
     제거
    0.11
    Activations Density 0.007%

    No Known Activations