© 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. 44944
    Prev
    Next
    INDEX
    Explanations

    case

    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
     dispenser
    -0.10
     فوائد
    -0.09
     whispers
    -0.09
     sneak
    -0.09
    notify
    -0.09
     pensamentos
    -0.08
    _notify
    -0.08
     unused
    -0.08
    goo
    -0.08
    .Notify
    -0.08
    POSITIVE LOGITS
    案例
    0.14
     사례
    0.13
     comparative
    0.11
     Comparative
    0.11
     Selected
    0.11
     selected
    0.11
    ศึกษ
    0.10
     exemplary
    0.10
     بررسی
    0.10
     examined
    0.10
    Activations Density 0.031%

    No Known Activations