© 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. 23-RESID-POST-AA
    11. 51840
    Prev
    Next
    INDEX
    Explanations

    say "symmetric"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orientation
    -0.09
     перевод
    -0.08
     Trans
    -0.08
     transformations
    -0.08
     anis
    -0.08
     orientation
    -0.08
     Fin
    -0.08
     Transformation
    -0.08
     Conservation
    -0.08
     Transform
    -0.08
    POSITIVE LOGITS
    -s
    0.22
    s
    0.19
    _s
    0.18
    	s
    0.18
    .s
    0.14
    ,s
    0.13
     ಸ
    0.13
    )s
    0.13
    "s
    0.12
    :s
    0.12
    Activations Density 0.056%

    No Known Activations