© 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. 48048
    Prev
    Next
    INDEX
    Explanations

    Friedman

    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
     palma
    -0.09
     acom
    -0.09
     informática
    -0.09
    ACO
    -0.09
    aird
    -0.08
     acr
    -0.08
     robotics
    -0.08
     acqu
    -0.08
    -0.08
    ámos
    -0.08
    POSITIVE LOGITS
     Wat
    0.09
    Wat
    0.08
    .toolbar
    0.08
    Profes
    0.08
    研究
    0.08
     неод
    0.08
    -dr
    0.07
    慢
    0.07
     unpredict
    0.07
    浪
    0.07
    Activations Density 0.001%
    No Known Activations