© 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. 114123
    Prev
    Next
    INDEX
    Explanations

    conversational/bot instructions

    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
    系列
    -0.08
    hebung
    -0.08
    本科
    -0.08
    -0.07
    ajien
    -0.07
     Stiftung
    -0.07
    -growing
    -0.07
     Financing
    -0.07
     Breit
    -0.07
    -rounded
    -0.07
    POSITIVE LOGITS
     tal
    0.08
     conmigo
    0.08
     �
    0.08
     Gym
    0.08
    راح
    0.08
     eslint
    0.07
     हाल
    0.07
     gym
    0.07
     
    0.07
     guitar
    0.07
    Activations Density 0.003%
    No Known Activations