© 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. 54538
    Prev
    Next
    INDEX
    Explanations

    identifying differences

    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
    หล
    -0.09
     prestige
    -0.08
     impér
    -0.08
    umbre
    -0.08
    _fit
    -0.08
    Chance
    -0.08
    创造
    -0.07
     trap
    -0.07
     Doctors
    -0.07
     reinterpret
    -0.07
    POSITIVE LOGITS
     differences
    0.19
     Unterschiede
    0.18
     Differences
    0.17
     différences
    0.16
     diferencias
    0.16
     diferenças
    0.16
    .compare
    0.14
     difference
    0.14
     discrepancies
    0.14
     comparar
    0.14
    Activations Density 0.012%

    No Known Activations