© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-RESID-POST-AA
    11. 2823
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hel
    -0.09
     Hel
    -0.08
     Morales
    -0.08
     Green
    -0.08
     refill
    -0.07
     procedural
    -0.07
    OLS
    -0.07
    是什么
    -0.07
    实力
    -0.07
     proceeds
    -0.07
    POSITIVE LOGITS
     taut
    0.09
     absolv
    0.09
    lot
    0.08
     affairs
    0.08
     conducir
    0.07
    EEP
    0.07
    hon
    0.07
     tart
    0.07
     alimentación
    0.07
     imprisonment
    0.07
    Activations Density 0.240%

    No Known Activations