© 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. 11-RESID-POST-AA
    11. 112404
    Prev
    Next
    INDEX
    Explanations

    Squaring numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ді
    -0.08
     wer
    -0.08
    vs
    -0.08
    411
    -0.07
     Оч
    -0.07
     Viol
    -0.07
     Lift
    -0.07
    ң
    -0.07
     viol
    -0.07
     Esk
    -0.07
    POSITIVE LOGITS
     rek
    0.08
     fenn
    0.08
     kerran
    0.08
     bono
    0.08
     crude
    0.08
     hil
    0.08
    dern
    0.08
     dulu
    0.07
    ിയാണ്
    0.07
     ars
    0.07
    Activations Density 0.021%

    No Known Activations