© 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. 7-RESID-POST-AA
    11. 1110
    Prev
    Next
    INDEX
    Explanations

    horizontal line separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soaking
    -0.08
    ree
    -0.08
     logr
    -0.07
     logarith
    -0.07
     Emmanuel
    -0.07
     aze
    -0.07
    ogg
    -0.07
     advocaat
    -0.07
    ാവ
    -0.07
    cee
    -0.07
    POSITIVE LOGITS
     ambul
    0.08
     blurry
    0.08
    hg
    0.08
    acceler
    0.08
     공동
    0.08
     numb
    0.07
     blurred
    0.07
     đứng
    0.07
    事实
    0.07
    "id
    0.07
    Activations Density 0.002%

    No Known Activations