© 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. 818
    Prev
    Next
    INDEX
    Explanations

    padding

    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
     Pare
    -0.08
    Pare
    -0.08
    ിലൂടെ
    -0.08
     кос
    -0.07
     pare
    -0.07
     통해
    -0.07
     Seng
    -0.07
     സര്
    -0.07
     overwhelming
    -0.07
     impover
    -0.07
    POSITIVE LOGITS
     CSV
    0.08
    -semibold
    0.08
    、安全
    0.08
     potassium
    0.08
    .Accept
    0.07
     receptors
    0.07
     SNP
    0.07
     csv
    0.07
     OBJ
    0.07
     وظائف
    0.07
    Activations Density 0.010%

    No Known Activations