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. 11678
    Prev
    Next
    INDEX
    Explanations

    Drivers

    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
     �
    -0.09
     व्यवहार
    -0.08
    หล
    -0.08
    mouth
    -0.08
     Otto
    -0.07
    _OFF
    -0.07
    λλη
    -0.07
     αυ
    -0.07
    [offset
    -0.07
    стве
    -0.07
    POSITIVE LOGITS
     firmware
    0.09
    厂
    0.08
    更新
    0.08
     שלך
    0.08
     my
    0.08
     обнов
    0.08
    Firmware
    0.07
     kumpanya
    0.07
     nourish
    0.07
     optimize
    0.07
    Activations Density 0.004%

    No Known Activations