© 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 EvalsExportsAPI 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. 20454
    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
     particular
    -0.09
     particularly
    -0.09
    ätzlich
    -0.08
     typical
    -0.08
     همچنین
    -0.08
     accompanying
    -0.08
     comparatively
    -0.08
     especially
    -0.08
     daarnaast
    -0.08
    谨
    -0.08
    POSITIVE LOGITS
     devient
    0.13
     became
    0.13
     becomes
    0.13
     결국
    0.12
     devenir
    0.12
     أصبح
    0.12
    ിലേക്ക്
    0.12
     become
    0.12
     divent
    0.12
     convertirse
    0.12
    Activations Density 0.019%

    No Known Activations