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. 23-RESID-POST-AA
    6. 97972
    Prev
    Next
    INDEX
    Explanations

    Arabic; marketing and business

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    901
    -0.08
    894
    -0.08
     cosmetic
    -0.08
     partic
    -0.08
     authorize
    -0.07
    965
    -0.07
    izante
    -0.07
     ayo
    -0.07
    641
    -0.07
     assume
    -0.07
    POSITIVE LOGITS
    ذب
    0.14
    لب
    0.13
    تاح
    0.11
    ني
    0.09
    رب
    0.09
    مع
    0.09
    ួយ
    0.09
    تمع
    0.09
    ਿਤ
    0.09
    تمد
    0.09
    Activations Density 0.001%

    No Known Activations