© 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. 21024
    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
    ITH
    -0.08
    IDAD
    -0.07
    /g
    -0.07
     duas
    -0.07
    OE
    -0.07
     vs
    -0.07
    ège
    -0.07
    AMOS
    -0.07
     செய்து
    -0.06
    /block
    -0.06
    POSITIVE LOGITS
     وغيرها
    0.38
     وغيره
    0.35
    など
    0.28
    等
    0.26
     लगायत
    0.25
     등의
    0.25
     등
    0.24
     आदि
    0.23
     समेत
    0.23
    その他
    0.22
    Activations Density 0.184%

    No Known Activations