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. 58360
    Prev
    Next
    INDEX
    Explanations

    dòng

    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
     stories
    -0.08
     histoires
    -0.07
     Workflow
    -0.07
     Reality
    -0.07
     dificultades
    -0.07
    -0.07
     journ
    -0.07
     গল্প
    -0.07
    Logical
    -0.07
     jurisdictions
    -0.07
    POSITIVE LOGITS
    ennia
    0.11
     تحتوي
    0.10
    Containing
    0.10
    Contains
    0.10
     contenant
    0.10
     يحتوي
    0.09
     содержит
    0.09
     જશે
    0.09
     contendo
    0.09
     containing
    0.09
    Activations Density 0.005%

    No Known Activations