© 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. 45214
    Prev
    Next
    INDEX
    Explanations

    arbitration

    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
     batter
    -0.08
     odnos
    -0.08
    iomanip
    -0.08
     mạnh
    -0.07
     intu
    -0.07
     polož
    -0.07
     El
    -0.07
     affich
    -0.07
    wash
    -0.07
    vom
    -0.07
    POSITIVE LOGITS
     tribun
    0.10
     विवाद
    0.09
     arbitration
    0.09
     Trib
    0.08
     jewelry
    0.08
     Tribunal
    0.08
     न्याय
    0.08
     Providence
    0.08
    ுக்
    0.08
     मामलों
    0.08
    Activations Density 0.004%

    No Known Activations