© 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. 26551
    Prev
    Next
    INDEX
    Explanations

    uniqueness

    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
    題
    -0.07
     open
    -0.07
     numer
    -0.07
    詳細
    -0.07
     ideale
    -0.07
     thrill
    -0.07
    님
    -0.07
     fragile
    -0.07
     undercover
    -0.07
     들
    -0.07
    POSITIVE LOGITS
    Duplicates
    0.14
     duplicates
    0.14
    duplicates
    0.13
     Duplicate
    0.13
    _duplicates
    0.12
    Duplicate
    0.12
    .Unique
    0.12
    uniq
    0.12
     uniq
    0.12
    uplicate
    0.11
    Activations Density 0.008%

    No Known Activations