© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47426
    Prev
    Next
    INDEX
    Explanations

    en-dash

    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
    招
    -0.08
     Lon
    -0.08
     участке
    -0.08
    eston
    -0.08
    isse
    -0.08
    ses
    -0.08
    uttle
    -0.08
    ifiable
    -0.07
     tender
    -0.07
    Lon
    -0.07
    POSITIVE LOGITS
    -notch
    0.11
    -tier
    0.10
    -flight
    0.09
    /top
    0.09
    สุด
    0.09
    -bottom
    0.09
    -density
    0.09
     elites
    0.08
     أعلى
    0.08
    -layer
    0.08
    Activations Density 0.022%

    No Known Activations