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. 76425
    Prev
    Next
    INDEX
    Explanations

    Code and URLs

    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
     Soo
    -0.08
     rejoindre
    -0.07
     spelling
    -0.07
     מקום
    -0.07
    halb
    -0.07
     Soy
    -0.07
     serviço
    -0.07
     Suddenly
    -0.07
     तौर
    -0.07
     Sud
    -0.07
    POSITIVE LOGITS
     terbaru
    0.08
     hv
    0.07
     v
    0.07
    グ
    0.07
     udp
    0.07
    最新版
    0.07
    /version
    0.07
    版本
    0.07
     Peaks
    0.07
    (version
    0.07
    Activations Density 0.006%

    No Known Activations