© 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. 79505
    Prev
    Next
    INDEX
    Explanations

    difficult

    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
     sø
    -0.08
     guns
    -0.08
     tử
    -0.07
     Telescope
    -0.07
     наконец
    -0.07
     Meyer
    -0.07
    finally
    -0.07
     telesc
    -0.07
     Junk
    -0.07
    DSL
    -0.07
    POSITIVE LOGITS
     khăn
    0.14
    難
    0.11
     difficult
    0.11
     difícil
    0.10
     difficile
    0.10
    困
    0.10
    难
    0.09
    /im
    0.09
     difíceis
    0.09
    igheter
    0.09
    Activations Density 0.047%

    No Known Activations