© 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. 11-RESID-POST-AA
    11. 25936
    Prev
    Next
    INDEX
    Explanations

    Visitors/Visits

    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
     deco
    -0.08
     fabrica
    -0.08
     química
    -0.08
     gars
    -0.08
     quadr
    -0.07
     التعب
    -0.07
    废
    -0.07
     PARAM
    -0.07
     dê
    -0.07
     MIC
    -0.07
    POSITIVE LOGITS
     visitors
    0.13
     visitantes
    0.13
     visiteurs
    0.13
     bezoekers
    0.13
     Besucher
    0.13
     посет
    0.13
     방문
    0.12
     ziyaret
    0.12
    Visitor
    0.12
    visitor
    0.12
    Activations Density 0.030%

    No Known Activations