© 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. 64626
    Prev
    Next
    INDEX
    Explanations

    �

    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
     Lesser
    -0.09
     zumindest
    -0.08
    _descr
    -0.08
    WORLD
    -0.08
     여자
    -0.08
    女士
    -0.07
     ലോക
    -0.07
    [MAX
    -0.07
     Czech
    -0.07
     Emanuel
    -0.07
    POSITIVE LOGITS
     pitfalls
    0.08
     orientar
    0.08
     blindness
    0.07
    全面
    0.07
     direcion
    0.07
     hindsight
    0.07
     вооруж
    0.07
    طيع
    0.07
     profitable
    0.07
     topical
    0.07
    Activations Density 0.004%

    No Known Activations