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. 15-RESID-POST-AA
    6. 19162
    Prev
    Next
    INDEX
    Explanations

    limited resources and geography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     because
    -0.09
    因为
    -0.09
    porque
    -0.08
    _sk
    -0.07
     fata
    -0.07
    세요
    -0.07
    sia
    -0.07
    ')↵//
    -0.07
    DEP
    -0.07
    because
    -0.07
    POSITIVE LOGITS
     necess
    0.11
     ולכן
    0.11
    ,需要
    0.10
     ولذلك
    0.10
    只能
    0.10
     Поэтому
    0.09
     nécess
    0.09
     требуют
    0.09
     ต้อง
    0.09
     לכן
    0.09
    Activations Density 0.014%

    No Known Activations