© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91506
    Prev
    Next
    INDEX
    Explanations

    activity

    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
     horas
    -0.08
     frameworks
    -0.07
     الأبيض
    -0.07
     Donovan
    -0.07
     blauwe
    -0.07
     running
    -0.07
     Mend
    -0.07
    itado
    -0.07
     dissent
    -0.07
    hoot
    -0.07
    POSITIVE LOGITS
     Magdalena
    0.08
     finder
    0.08
     volupt
    0.07
     alcool
    0.07
     comparator
    0.07
     ആഘ
    0.07
    -register
    0.07
    Checker
    0.07
     Wetter
    0.07
    ->_
    0.07
    Activations Density 0.002%

    No Known Activations