© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 63226
    Prev
    Next
    INDEX
    Explanations

    Code/Software snippets

    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
     Medicare
    -0.13
     चिकित्स
    -0.11
     physicians
    -0.10
     پزش
    -0.10
     의료
    -0.10
     Healthcare
    -0.10
     insurer
    -0.10
    Healthcare
    -0.10
     healthcare
    -0.10
     clinicians
    -0.10
    POSITIVE LOGITS
     Bukkit
    0.15
    .discord
    0.14
     Terraria
    0.14
    Minecraft
    0.14
     Minecraft
    0.14
     minecraft
    0.13
     Discord
    0.13
    Discord
    0.13
    玩家
    0.13
     Fortnite
    0.13
    Activations Density 0.083%

    No Known Activations