© 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. 22414
    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
     tendrá
    -0.10
    ]:↵
    -0.09
     tendrán
    -0.09
    њу
    -0.09
    ərində
    -0.09
    }{↵
    -0.09
     terão
    -0.09
     estarán
    -0.09
    ]:↵↵
    -0.09
    :↵//↵//
    -0.08
    POSITIVE LOGITS
    是
    0.13
     is
    0.13
     是
    0.12
     ->
    0.11
     হলো
    0.11
    คือ
    0.10
    ->
    0.10
     হল
    0.10
     →
    0.09
     adalah
    0.09
    Activations Density 0.043%

    No Known Activations