© 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. 30486
    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
    estellt
    -0.08
     ultraviolet
    -0.08
     ваз
    -0.08
     настрой
    -0.07
     nejs
    -0.07
     discs
    -0.07
    angel
    -0.07
    ulter
    -0.07
    illons
    -0.07
     directing
    -0.07
    POSITIVE LOGITS
     sanity
    0.09
    验证
    0.08
    .Test
    0.08
    	test
    0.08
    .verify
    0.08
    驗
    0.08
    _matches
    0.08
    /test
    0.08
    验
    0.08
     correctness
    0.07
    Activations Density 0.022%

    No Known Activations