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. 49398
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     شاه
    -0.09
    েষ্ট
    -0.09
    aghetti
    -0.08
    หัว
    -0.08
     capo
    -0.08
     प्रहरी
    -0.08
     Зас
    -0.08
    -0.08
     গণ
    -0.08
    .euler
    -0.08
    POSITIVE LOGITS
     markets
    0.25
     시장
    0.24
    市场
    0.24
     рынок
    0.24
     рынка
    0.24
    市場
    0.23
     market
    0.23
     mercados
    0.23
     mercado
    0.22
     बाजार
    0.22
    Activations Density 0.108%

    No Known Activations