© 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. 3-RESID-POST-AA
    11. 2997
    Prev
    Next
    INDEX
    Explanations

    bist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constantly
    -0.08
    vermittlung
    -0.07
    צר
    -0.07
     voortdurend
    -0.07
    constitution
    -0.07
     ก
    -0.07
     acreage
    -0.07
    레스
    -0.07
    Har
    -0.07
    	mv
    -0.07
    POSITIVE LOGITS
     sola
    0.08
     whistle
    0.08
    Dat
    0.07
     Reactive
    0.07
     Prot
    0.07
     Cylinder
    0.07
     Cer
    0.07
     keres
    0.07
     Cyl
    0.07
     Wolfs
    0.07
    Activations Density 0.000%

    No Known Activations