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. 58675
    Prev
    Next
    INDEX
    Explanations

    归

    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
     boj
    -0.08
    .T
    -0.08
    (二
    -0.08
    wek
    -0.07
     svc
    -0.07
    we
    -0.07
    tur
    -0.07
     frag
    -0.07
     hydrochlor
    -0.07
     Lambert
    -0.07
    POSITIVE LOGITS
     organizes
    0.09
     đây
    0.08
    ীক্ষ
    0.08
    ίν
    0.08
    归
    0.07
    ears
    0.07
    िण
    0.07
     सही
    0.07
    属于
    0.07
    整理
    0.07
    Activations Density 0.004%

    No Known Activations