© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 112411
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     abortions
    -0.08
     introductions
    -0.08
    会上
    -0.08
    papers
    -0.08
    公开
    -0.08
     Verkaufs
    -0.08
    érios
    -0.08
     impart
    -0.08
    .jobs
    -0.07
    Illinois
    -0.07
    POSITIVE LOGITS
     sqrt
    0.13
    sqrt
    0.11
    √
    0.10
    .sqrt
    0.10
     √
    0.09
    บาง
    0.08
    qrt
    0.08
     RMS
    0.08
    0.08
     nifty
    0.08
    Activations Density 0.066%

    No Known Activations