© 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. 44428
    Prev
    Next
    INDEX
    Explanations

    language terminology

    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
     repayments
    -0.09
     bango
    -0.08
     Unterricht
    -0.08
     debit
    -0.07
    -confidence
    -0.07
     Dys
    -0.07
     공연
    -0.07
     Debit
    -0.07
     studenti
    -0.07
     Integrity
    -0.07
    POSITIVE LOGITS
    aken
    0.07
    šķ
    0.07
     expans
    0.07
     говоря
    0.07
    副
    0.07
    版
    0.07
    ache
    0.07
     pren
    0.07
    Queues
    0.07
    Patent
    0.07
    Activations Density 0.008%

    No Known Activations