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. 102765
    Prev
    Next
    INDEX
    Explanations

    manufacturing and environment

    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
     using
    -0.09
     acting
    -0.09
     v
    -0.08
    *
    -0.08
    _L
    -0.08
    _ACTION
    -0.08
     Newman
    -0.08
     (
    -0.07
    _
    -0.07
     looking
    -0.07
    POSITIVE LOGITS
    材料
    0.13
     materiales
    0.11
     Herstellung
    0.10
     تصنيع
    0.10
    材
    0.10
    materials
    0.09
     materiais
    0.09
     तयारी
    0.09
     материалы
    0.09
     materialen
    0.09
    Activations Density 0.016%

    No Known Activations