© 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. 129274
    Prev
    Next
    INDEX
    Explanations

    dividing planes, calculating regions

    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
    asin
    -0.08
    ตร
    -0.08
    bond
    -0.08
    ば
    -0.07
     کود
    -0.07
    memcmp
    -0.07
     Pitch
    -0.07
     gemeinsame
    -0.07
    共同
    -0.07
    к
    -0.07
    POSITIVE LOGITS
     aumento
    0.09
     увелич
    0.09
     incremento
    0.09
     aumenta
    0.09
     aument
    0.09
    .increment
    0.09
     incremental
    0.08
     वृद्धि
    0.08
     증가
    0.08
    Increasing
    0.08
    Activations Density 0.008%

    No Known Activations