© 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. 129166
    Prev
    Next
    INDEX
    Explanations

    expressed

    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
     establishes
    -0.08
     Protest
    -0.08
    marks
    -0.07
    hors
    -0.07
     fina
    -0.07
    -inner
    -0.07
    yə
    -0.07
     refurbishment
    -0.07
    respons
    -0.07
    🏻
    -0.07
    POSITIVE LOGITS
    形式
    0.08
    ప్ర
    0.08
    符
    0.08
     intangible
    0.07
    ಲ್ಲಿ
    0.07
    avnom
    0.07
    ซ
    0.07
    ಪ್ರ
    0.07
    succ
    0.07
     ดิ
    0.07
    Activations Density 0.012%

    No Known Activations