Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98176
    Prev
    Next
    INDEX
    Explanations

    say "ел"

    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
     charts
    -0.08
    MIS
    -0.08
    RE
    -0.07
     grapefruit
    -0.07
     Mu
    -0.07
    parison
    -0.07
     verfol
    -0.07
    ro
    -0.07
     anot
    -0.07
     Trades
    -0.07
    POSITIVE LOGITS
    ел
    0.13
    ёл
    0.12
    ело
    0.10
    елиться
    0.10
    élite
    0.10
    еля
    0.10
    еле
    0.10
    ЕЛ
    0.10
    ેલ
    0.09
    ેલા
    0.09
    Activations Density 0.001%

    No Known Activations