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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 919
    Prev
    Next
    INDEX
    Explanations

    end

    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
     Roblox
    -0.08
     acerca
    -0.07
    gles
    -0.07
     yen
    -0.07
    üns
    -0.07
     Exchange
    -0.07
     তৈরি
    -0.07
     lega
    -0.07
     соң
    -0.07
     Color
    -0.07
    POSITIVE LOGITS
    ascending
    0.08
     vastly
    0.08
     endforeach
    0.08
    遍
    0.07
    天空
    0.07
    plac
    0.07
    ambled
    0.07
     राजधानी
    0.07
     Един
    0.07
    Malformed
    0.07
    Activations Density 0.012%

    No Known Activations