© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26612
    Prev
    Next
    INDEX
    Explanations

    pair production

    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
    ,F
    -0.08
    ,f
    -0.07
    時間
    -0.07
    .De
    -0.07
    ,S
    -0.07
     czasu
    -0.07
    ningar
    -0.07
     schedules
    -0.07
    levels
    -0.07
    ascimento
    -0.07
    POSITIVE LOGITS
     Río
    0.09
    РИ
    0.09
     Investors
    0.09
    сти
    0.08
    Bindings
    0.08
    ольно
    0.08
     cannabino
    0.08
    /USD
    0.08
     cannabidiol
    0.08
     cocaine
    0.08
    Activations Density 0.001%

    No Known Activations