© 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. 23-RESID-POST-AA
    11. 6692
    Prev
    Next
    INDEX
    Explanations

    say "the ending -orship"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ولایت
    -0.08
    -pro
    -0.08
    улу
    -0.08
     quốc
    -0.08
     Dövlət
    -0.08
    ვალი
    -0.08
     Sele
    -0.07
    ынч
    -0.07
    ôi
    -0.07
    _prob
    -0.07
    POSITIVE LOGITS
    orship
    0.15
    orial
    0.10
     entrepreneurship
    0.09
    eurs
    0.09
    UFACTUR
    0.08
    or
    0.08
    ors
    0.08
    ress
    0.08
    orat
    0.08
     entrepreneur
    0.08
    Activations Density 0.001%

    No Known Activations