© 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. 99621
    Prev
    Next
    INDEX
    Explanations

    caricatures

    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
    aterra
    -0.09
     Jus
    -0.07
    <Record
    -0.07
     depleted
    -0.07
     coul
    -0.07
    Leaks
    -0.07
     permit
    -0.07
    允许
    -0.07
     vaso
    -0.07
     Scroll
    -0.07
    POSITIVE LOGITS
     caric
    0.13
     exagger
    0.11
     exaggerated
    0.09
     sketch
    0.08
     Armen
    0.08
    ประช
    0.08
     fingerprint
    0.08
     fisherman
    0.08
     cartoons
    0.08
     الفنان
    0.08
    Activations Density 0.007%

    No Known Activations