Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56186
    Prev
    Next
    INDEX
    Explanations

    deco

    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
     PHPUnit
    -0.08
    atten
    -0.08
     ort
    -0.07
    _TX
    -0.07
     reporters
    -0.07
     antibiotic
    -0.07
     attenuation
    -0.07
     Messenger
    -0.07
     reporter
    -0.07
     Gram
    -0.07
    POSITIVE LOGITS
    -inspired
    0.09
     decad
    0.09
    宇
    0.09
     корпуса
    0.09
     aviation
    0.09
    时期
    0.09
     empres
    0.08
     aport
    0.08
     Tribal
    0.08
    飛
    0.08
    Activations Density 0.002%

    No Known Activations