© 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. 730
    Prev
    Next
    INDEX
    Explanations

    to

    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
    .listdir
    -0.09
    Watching
    -0.08
     Watching
    -0.08
    Checklist
    -0.08
     Malayalam
    -0.08
    晓
    -0.08
     haja
    -0.08
     errands
    -0.08
    -cover
    -0.08
     Checklist
    -0.08
    POSITIVE LOGITS
     aceler
    0.11
     faster
    0.11
     ускор
    0.10
     capable
    0.10
     acceler
    0.10
     accelerated
    0.09
     capables
    0.09
     acelerar
    0.09
     accél
    0.09
    ,max
    0.09
    Activations Density 0.004%

    No Known Activations