© 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. 21657
    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
    Force
    -0.07
    for
    -0.07
    勇
    -0.07
     valor
    -0.07
     SUCH
    -0.07
     folgenden
    -0.07
     таким
    -0.07
     force
    -0.07
    그리고
    -0.07
     invariant
    -0.07
    POSITIVE LOGITS
     משום
    0.10
     မွ
    0.10
    ​មាន
    0.10
     kufuneka
    0.10
     מען
    0.10
     մենք
    0.10
     קען
    0.09
    ումն
    0.09
     болсо
    0.09
     պետք
    0.09
    Activations Density 0.003%

    No Known Activations