© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 22010
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anjem
    -0.08
     примерно
    -0.07
    oldoende
    -0.07
     resized
    -0.07
     ылай
    -0.07
    ক্রান্ত
    -0.07
     सोमवार
    -0.07
     تقريب
    -0.07
     uygun
    -0.07
     рәс
    -0.07
    POSITIVE LOGITS
     unique
    0.33
     uniqueness
    0.33
    Unique
    0.33
     distinctive
    0.32
     Unique
    0.32
     einzigart
    0.32
     uniek
    0.31
    _unique
    0.31
     unieke
    0.31
    unique
    0.31
    Activations Density 0.116%

    No Known Activations