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. 60994
    Prev
    Next
    INDEX
    Explanations

    help

    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
    发行
    -0.08
     Devon
    -0.08
     consequential
    -0.08
    ヒ
    -0.08
     Iso
    -0.08
     Hig
    -0.08
    kr
    -0.08
    ��
    -0.07
    reven
    -0.07
    rapid
    -0.07
    POSITIVE LOGITS
    🏼
    0.09
    verlening
    0.08
    0.08
    desk
    0.08
    不到
    0.08
    _needed
    0.07
     көрсету
    0.07
    اؤ
    0.07
     त्य
    0.07
     گذا
    0.07
    Activations Density 0.039%

    No Known Activations