© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47978
    Prev
    Next
    INDEX
    Explanations

    at

    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
    ્તિ
    -0.08
     उनसे
    -0.08
     lacks
    -0.08
    uchen
    -0.08
    maz
    -0.07
     tournament
    -0.07
    Tournament
    -0.07
    Hmm
    -0.07
    mén
    -0.07
     मिलने
    -0.07
    POSITIVE LOGITS
    .Retention
    0.08
     AAC
    0.08
     Daddy
    0.08
     groundwork
    0.08
     Chim
    0.08
     بذ
    0.08
     DBA
    0.08
     Bosco
    0.07
     جانب
    0.07
     Brem
    0.07
    Activations Density 0.001%

    No Known Activations