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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 108794
    Prev
    Next
    INDEX
    Explanations

    print

    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
     Crane
    -0.08
     paik
    -0.08
     analytic
    -0.07
    ันท
    -0.07
     +/-
    -0.07
     debilit
    -0.07
     Petrol
    -0.07
     nchi
    -0.07
     Miy
    -0.07
     Chance
    -0.07
    POSITIVE LOGITS
    出来
    0.11
     המצ
    0.08
     hiking
    0.08
     ulang
    0.07
    ированных
    0.07
    ispers
    0.07
     verkl
    0.07
    tops
    0.07
     ചെയ്ത്
    0.07
     fidél
    0.07
    Activations Density 0.010%

    No Known Activations