© 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. 19303
    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
     ჩვენი
    -0.09
     mūsų
    -0.09
     our
    -0.09
     нашей
    -0.09
     우리
    -0.09
    今晚
    -0.08
    เรา
    -0.08
     Our
    -0.08
     anyị
    -0.08
     আমাদের
    -0.08
    POSITIVE LOGITS
     étrange
    0.12
     foreigners
    0.12
     weird
    0.12
     strange
    0.11
    外国
    0.11
     asing
    0.11
    陌
    0.11
     dudes
    0.11
     unfamiliar
    0.11
    -colored
    0.10
    Activations Density 0.042%

    No Known Activations