© 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. 47720
    Prev
    Next
    INDEX
    Explanations

    -

    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
     μετά
    -0.08
     pracht
    -0.08
    -skilled
    -0.08
     remains
    -0.08
     directs
    -0.08
     repl
    -0.08
    енным
    -0.08
    prep
    -0.07
     kommenden
    -0.07
    -cre
    -0.07
    POSITIVE LOGITS
    istor
    0.08
     Sør
    0.08
     monopoly
    0.08
     Adler
    0.07
     Winchester
    0.07
     Maxwell
    0.07
     Monopoly
    0.07
     çift
    0.07
     істор
    0.07
    olari
    0.07
    Activations Density 0.029%

    No Known Activations