Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 88265
    Prev
    Next
    INDEX
    Explanations

    ISO standards

    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
     اختیار
    -0.10
    หน้
    -0.08
     ótima
    -0.08
    去了
    -0.08
    পূর্ণ
    -0.08
     dívida
    -0.08
    .stroke
    -0.08
    ขาย
    -0.07
     carbohydrate
    -0.07
    اً
    -0.07
    POSITIVE LOGITS
    41
    0.09
    21
    0.09
    68
    0.09
    81
    0.08
    36
    0.08
    61
    0.08
    _UID
    0.08
    18
    0.08
    608
    0.08
    554
    0.08
    Activations Density 0.007%

    No Known Activations