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. 98505
    Prev
    Next
    INDEX
    Explanations

    say "phí"

    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
    Totals
    -0.08
    mainder
    -0.08
    留
    -0.08
     totals
    -0.08
     col
    -0.07
     harvest
    -0.07
    期期
    -0.07
    -total
    -0.07
     ocean
    -0.07
     fluorescence
    -0.07
    POSITIVE LOGITS
     phí
    0.11
    არჯ
    0.10
     Ph
    0.10
    .ph
    0.09
    روف
    0.08
    ്യാസ
    0.08
    ర్చ
    0.08
    _Ph
    0.08
    ефон
    0.08
    .Ph
    0.08
    Activations Density 0.002%

    No Known Activations