© 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. 25165
    Prev
    Next
    INDEX
    Explanations

    least common multiple problems

    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
     genauso
    -0.09
     parce
    -0.08
     의미
    -0.08
    enangkan
    -0.08
     зимой
    -0.07
    出售
    -0.07
    嘴
    -0.07
     intent
    -0.07
     команда
    -0.07
     du
    -0.07
    POSITIVE LOGITS
     gcd
    0.11
     harmony
    0.10
     qaba
    0.09
    Harmony
    0.09
     ګډ
    0.09
    .union
    0.09
     armon
    0.09
     Harmony
    0.09
    Comb
    0.08
     beträgt
    0.08
    Activations Density 0.050%

    No Known Activations