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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 120320
    Prev
    Next
    INDEX
    Explanations

    scale

    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
     exposição
    -0.08
    gja
    -0.08
    das
    -0.07
    Customize
    -0.07
     Exposure
    -0.07
    صح
    -0.07
     dazu
    -0.07
     OECD
    -0.07
     Sicher
    -0.07
    Brazil
    -0.07
    POSITIVE LOGITS
    尺寸
    0.09
     размера
    0.09
     meters
    0.09
     изображ
    0.09
     размеры
    0.09
     upwards
    0.08
     filesize
    0.08
     afbeelding
    0.08
     afbeeldingen
    0.08
     Вал
    0.08
    Activations Density 0.005%

    No Known Activations