© 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. 13077
    Prev
    Next
    INDEX
    Explanations

    依

    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
    把
    -0.08
     Cla
    -0.08
     nb
    -0.08
     dispers
    -0.08
     enf
    -0.07
     Antoine
    -0.07
     sé
    -0.07
     тв
    -0.07
     Feder
    -0.07
     ít
    -0.07
    POSITIVE LOGITS
    ச்
    0.08
    靠
    0.07
    صل
    0.07
    -cont
    0.07
     Zah
    0.07
    kommen
    0.07
     lifts
    0.07
     lift
    0.07
     deprivation
    0.07
     Bab
    0.07
    Activations Density 0.007%

    No Known Activations