© 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. 13193
    Prev
    Next
    INDEX
    Explanations

    Plan

    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
    834
    -0.09
     VC
    -0.09
    Who
    -0.08
     communicate
    -0.08
    VC
    -0.08
    WR
    -0.08
    -wire
    -0.07
    RPM
    -0.07
    Qui
    -0.07
     Proverbs
    -0.07
    POSITIVE LOGITS
     expend
    0.08
    gra
    0.08
     sade
    0.08
    udsman
    0.08
     бума
    0.08
     firmado
    0.07
    融合
    0.07
    ថ
    0.07
    ède
    0.07
    poly
    0.07
    Activations Density 0.020%

    No Known Activations