© 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. 18952
    Prev
    Next
    INDEX
    Explanations

    可以

    np_max-act-logits · gemini-2.0-flash
    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
     can
    -0.26
     would
    -0.19
     could
    -0.19
     may
    -0.18
     will
    -0.18
     might
    -0.18
     must
    -0.17
     should
    -0.16
     يمكن
    -0.15
    	can
    -0.15
    POSITIVE LOGITS
     быть
    0.17
    得到
    0.17
    通过
    0.16
     být
    0.16
    看到
    0.15
     essere
    0.15
     być
    0.15
     būti
    0.15
    很好
    0.14
     быць
    0.14
    Activations Density 0.026%

    No Known Activations