© 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. 69205
    Prev
    Next
    INDEX
    Explanations

    out of the box

    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
     ntau
    -0.09
    ilation
    -0.08
     IL
    -0.08
     agrav
    -0.08
    τηση
    -0.07
    itrust
    -0.07
    患
    -0.07
     Awọn
    -0.07
     dpi
    -0.07
     matern
    -0.07
    POSITIVE LOGITS
     unconventional
    0.17
     innovative
    0.13
     deviation
    0.13
    Deviation
    0.13
     afwijk
    0.12
     deviations
    0.12
    Innovation
    0.12
     boldly
    0.12
     нест
    0.12
     необы
    0.12
    Activations Density 0.126%

    No Known Activations