© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68192
    Prev
    Next
    INDEX
    Explanations

    coming into being

    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
    েবল
    -0.07
    есп
    -0.07
     capability
    -0.07
     সক্ষম
    -0.07
     capabilities
    -0.07
     neighbors
    -0.07
     Çok
    -0.07
    boxes
    -0.07
    েট
    -0.07
    neighbors
    -0.07
    POSITIVE LOGITS
     возникновения
    0.13
     genesis
    0.13
     origins
    0.12
     ontstaan
    0.12
     entstanden
    0.11
    Origins
    0.11
     entstand
    0.10
     Origins
    0.10
     motivations
    0.10
     inspirations
    0.10
    Activations Density 0.086%

    No Known Activations