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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102904
    Prev
    Next
    INDEX
    Explanations

    variety

    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
     Nicolas
    -0.08
     arkadaş
    -0.07
     cognition
    -0.07
     amigos
    -0.07
     Lourdes
    -0.07
    chema
    -0.07
     conscientes
    -0.07
    撃
    -0.07
    vu
    -0.07
    090
    -0.07
    POSITIVE LOGITS
     macam
    0.09
    汁
    0.09
     innen
    0.09
     أنواع
    0.09
    排列
    0.08
     сорт
    0.08
     sosai
    0.08
     tersedia
    0.08
     donuts
    0.08
     assortment
    0.08
    Activations Density 0.055%

    No Known Activations