© 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. 69584
    Prev
    Next
    INDEX
    Explanations

    recover

    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
     проводится
    -0.08
     élect
    -0.08
     analiz
    -0.08
    োনা
    -0.08
     folie
    -0.08
    atoire
    -0.08
    ровод
    -0.07
     Versorgung
    -0.07
     Zentrum
    -0.07
     নজ
    -0.07
    POSITIVE LOGITS
     کولو
    0.08
     revert
    0.08
     reverting
    0.08
     thanks
    0.08
     gracias
    0.08
    回来
    0.08
     retaining
    0.08
    persist
    0.08
    Mr
    0.08
     retention
    0.08
    Activations Density 0.009%

    No Known Activations