© 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. 786
    Prev
    Next
    INDEX
    Explanations

    aging and telomeres

    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
     surveys
    -0.08
     roasted
    -0.08
     survey
    -0.08
     ظرف
    -0.08
     canv
    -0.08
     worship
    -0.08
    Survey
    -0.08
    asco
    -0.08
    lıq
    -0.08
     مساعد
    -0.07
    POSITIVE LOGITS
     longitud
    0.09
     Length
    0.09
     дли
    0.08
     length
    0.08
     बढ़
    0.08
    Length
    0.08
     Maintenance
    0.08
    Maintenance
    0.08
    长度
    0.08
     upkeep
    0.08
    Activations Density 0.001%

    No Known Activations