© 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. 94732
    Prev
    Next
    INDEX
    Explanations

    choice

    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
    ivere
    -0.09
    azio
    -0.08
    bow
    -0.08
    IVED
    -0.08
    .mix
    -0.07
     rss
    -0.07
    бря
    -0.07
    бед
    -0.07
     erection
    -0.07
     raft
    -0.07
    POSITIVE LOGITS
    性质
    0.09
    式
    0.09
     qualifier
    0.08
    课程
    0.08
    版
    0.08
    考试
    0.07
     carreira
    0.07
     calculus
    0.07
     baff
    0.07
    _iterator
    0.07
    Activations Density 0.004%

    No Known Activations