© 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. 113264
    Prev
    Next
    INDEX
    Explanations

    filter

    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
     Clipboard
    -0.08
     arr
    -0.08
     приш
    -0.08
     anno
    -0.08
     arra
    -0.07
     вклад
    -0.07
    ょう
    -0.07
     суд
    -0.07
     ged
    -0.07
     увид
    -0.07
    POSITIVE LOGITS
    \Migrations
    0.09
     promo
    0.09
     Mustang
    0.08
    _hal
    0.08
     truncate
    0.08
    Half
    0.08
     Nina
    0.08
     Porta
    0.08
     Half
    0.08
     Heck
    0.08
    Activations Density 0.001%

    No Known Activations