© 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. 54500
    Prev
    Next
    INDEX
    Explanations

    basketball seasons, years

    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
    Reporter
    -0.08
     retrou
    -0.07
     שק
    -0.07
     návr
    -0.07
     Investigator
    -0.07
    可
    -0.07
     чему
    -0.07
     evangel
    -0.07
    �
    -0.07
     Reporter
    -0.07
    POSITIVE LOGITS
     poorer
    0.08
    يره
    0.08
     fiscal
    0.08
    Transactions
    0.08
     ಅರ್�
    0.08
     distinction
    0.08
     commod
    0.08
    sport
    0.07
    τε
    0.07
    stag
    0.07
    Activations Density 0.027%

    No Known Activations