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. 106108
    Prev
    Next
    INDEX
    Explanations

    on

    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
     vett
    -0.08
     Illustrated
    -0.08
    ukwa
    -0.08
     vem
    -0.08
     Mila
    -0.07
     conscientious
    -0.07
     XK
    -0.07
    REFERRED
    -0.07
    maals
    -0.07
     revanche
    -0.07
    POSITIVE LOGITS
     ранее
    0.12
     توسط
    0.11
     wcześniej
    0.10
     sebelumnya
    0.10
     précéd
    0.09
     специально
    0.09
     недавно
    0.09
     anteriormente
    0.09
     bởi
    0.09
     вчера
    0.09
    Activations Density 0.154%

    No Known Activations