© 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. 129565
    Prev
    Next
    INDEX
    Explanations

    |

    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
    ்மை
    -0.08
     DOI
    -0.08
    近年来
    -0.07
     يعيش
    -0.07
     incont
    -0.07
     মর
    -0.07
     addicts
    -0.07
     supplied
    -0.07
    729
    -0.07
    őr
    -0.07
    POSITIVE LOGITS
    cheduled
    0.09
     semanal
    0.09
    安排
    0.09
     Week
    0.09
     Aktionen
    0.09
    予定
    0.09
     scheduled
    0.09
    .schedule
    0.09
     errands
    0.09
     Breakfast
    0.09
    Activations Density 0.027%

    No Known Activations