© 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 EvalsExportsAPI 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. 20698
    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
     notes
    -0.07
     milliers
    -0.07
    必要
    -0.07
    vast
    -0.07
    Notas
    -0.07
     los
    -0.07
     bancos
    -0.07
     las
    -0.07
     notas
    -0.07
     banco
    -0.07
    POSITIVE LOGITS
    �
    0.09
    -based
    0.09
    中旗
    0.09
    ๑
    0.08
    -inspired
    0.08
     હાલમાં
    0.08
    ინ
    0.08
    әң
    0.08
    ";//
    0.08
    alent
    0.08
    Activations Density 0.001%

    No Known Activations