© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103127
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stylish
    -0.20
    しゃれ
    -0.17
     elegant
    -0.17
     élégant
    -0.17
     elegante
    -0.17
     whimsical
    -0.17
     charming
    -0.16
     playful
    -0.16
     flavorful
    -0.16
     élég
    -0.16
    POSITIVE LOGITS
     پایین
    0.09
     HTTP
    0.08
    عدام
    0.08
    وسطة
    0.08
     BELOW
    0.07
     منتصف
    0.07
     килом
    0.07
     interruption
    0.07
     backend
    0.07
     دوسری
    0.07
    Activations Density 0.368%

    No Known Activations