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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23450
    Prev
    Next
    INDEX
    Explanations

    Hindu

    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
    突
    -0.09
     الكبيرة
    -0.08
     المشتر
    -0.07
     ხ
    -0.07
    KES
    -0.07
     muff
    -0.07
    سيق
    -0.07
    苹果
    -0.07
    ujesz
    -0.07
     وسي
    -0.07
    POSITIVE LOGITS
     धार्मिक
    0.09
     hym
    0.08
     bestemm
    0.08
     RP
    0.08
     Eccles
    0.08
     theological
    0.08
     tradition
    0.08
     theology
    0.08
     rituals
    0.08
     prepar
    0.08
    Activations Density 0.002%

    No Known Activations