© 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. 11-RESID-POST-AA
    11. 71254
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    UAL
    -0.07
     Balanced
    -0.07
     खरी
    -0.07
     வரை
    -0.07
    Unlocked
    -0.07
    Orientation
    -0.07
    Advanced
    -0.07
    बाक
    -0.07
     bachelor
    -0.07
    Intl
    -0.07
    POSITIVE LOGITS
     horribly
    0.10
     tragic
    0.10
     fatal
    0.09
     disastr
    0.09
    灾
    0.09
     өнім
    0.09
     mau
    0.09
     məhs
    0.09
     ઉત્પાદ
    0.09
     гиб
    0.09
    Activations Density 0.041%

    No Known Activations