© 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. 54357
    Prev
    Next
    INDEX
    Explanations

    .legend

    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
     étant
    -0.08
     medic
    -0.08
     ⇒
    -0.08
     being
    -0.08
    Being
    -0.08
     Mom
    -0.08
     bem
    -0.07
    yang
    -0.07
     advocated
    -0.07
     amb
    -0.07
    POSITIVE LOGITS
    burn
    0.09
    _fun
    0.08
    lv
    0.08
    �
    0.08
    �ে
    0.07
     ஆண்டு
    0.07
     precautions
    0.07
    (Animation
    0.07
    ountain
    0.07
     sure
    0.07
    Activations Density 0.002%

    No Known Activations