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. 12084
    Prev
    Next
    INDEX
    Explanations

    for

    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
     adag
    -0.09
     impro
    -0.07
     đồ
    -0.07
     despi
    -0.07
     EH
    -0.07
    	log
    -0.07
     EO
    -0.07
    };↵↵
    -0.07
     kuva
    -0.07
     clones
    -0.07
    POSITIVE LOGITS
    เพื่อ
    0.10
     للحصول
    0.09
     जाकर
    0.09
    查看更多
    0.08
    ើម្បី
    0.08
    erni
    0.08
     accomplishments
    0.08
     تعاون
    0.08
    Achievements
    0.08
    _confirmation
    0.08
    Activations Density 0.081%

    No Known Activations