© 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. 45362
    Prev
    Next
    INDEX
    Explanations

    tournament graphs and cycles

    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
     Homes
    -0.08
    vara
    -0.08
    妈妈
    -0.08
    ెన
    -0.08
    Plans
    -0.08
    Sans
    -0.08
     Família
    -0.08
    家庭
    -0.07
     familia
    -0.07
    Maison
    -0.07
    POSITIVE LOGITS
     rankings
    0.11
     victories
    0.11
     undefeated
    0.11
     જીત
    0.11
     winner
    0.11
     ranking
    0.10
     tournament
    0.10
    ournament
    0.10
    -ranking
    0.10
     defeated
    0.10
    Activations Density 0.012%

    No Known Activations