© 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. 29310
    Prev
    Next
    INDEX
    Explanations

    дети

    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
    Barrier
    -0.09
     방송
    -0.09
     SWOT
    -0.08
    　一
    -0.08
     tats
    -0.08
     rooft
    -0.08
     aérea
    -0.08
     للط
    -0.08
    ดาว
    -0.08
     barriers
    -0.07
    POSITIVE LOGITS
     deformation
    0.09
     Kaiser
    0.09
     arthritis
    0.09
     rheumatoid
    0.09
    _xpath
    0.08
     biomechanics
    0.08
    .xpath
    0.08
    ૂત
    0.08
    滚
    0.07
    (indent
    0.07
    Activations Density 0.087%

    No Known Activations