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. 111835
    Prev
    Next
    INDEX
    Explanations

    Border security

    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
    优惠
    -0.10
    励
    -0.09
     remedies
    -0.08
    字号
    -0.08
     generous
    -0.08
    ાન
    -0.08
     Nürn
    -0.08
    选号
    -0.08
     generosity
    -0.08
    体育彩票
    -0.08
    POSITIVE LOGITS
     ingest
    0.10
     оснащ
    0.08
     terrest
    0.08
     suction
    0.08
     traff
    0.08
     Enforcement
    0.08
    unker
    0.08
     पृथ
    0.07
     पाइ
    0.07
     enforcement
    0.07
    Activations Density 0.015%

    No Known Activations