© 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. 24719
    Prev
    Next
    INDEX
    Explanations

    integer bit width

    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
    Offline
    -0.09
    Inbound
    -0.08
     downturn
    -0.08
     turnover
    -0.08
     floral
    -0.08
     docking
    -0.08
    tractions
    -0.08
     hospitality
    -0.07
     müş
    -0.07
     touring
    -0.07
    POSITIVE LOGITS
     sizeof
    0.11
     endian
    0.10
     Sizes
    0.10
     sizes
    0.10
    sizeof
    0.10
    (sizeof
    0.09
     typedef
    0.09
     gcc
    0.09
    	sizeof
    0.09
    SIZE
    0.09
    Activations Density 0.006%

    No Known Activations