© 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. 110422
    Prev
    Next
    INDEX
    Explanations

    redirects

    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
    860
    -0.10
     볼
    -0.08
     amaz
    -0.07
     лише
    -0.07
     ps
    -0.07
     America's
    -0.07
    -of
    -0.06
    -Aug
    -0.06
    물이
    -0.06
    occi
    -0.06
    POSITIVE LOGITS
     permanently
    0.11
    永久
    0.10
     पुराने
    0.10
     dauerhaft
    0.10
     vieux
    0.09
     redirects
    0.09
     verhuis
    0.09
     중요한
    0.09
     Sache
    0.09
     définitivement
    0.09
    Activations Density 0.003%

    No Known Activations