© 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. 11-RESID-POST-AA
    11. 54592
    Prev
    Next
    INDEX
    Explanations

    Asking how to do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kir
    -0.08
     hona
    -0.08
     خواه
    -0.08
     à
    -0.08
     Asi
    -0.08
     دنبال
    -0.08
    еит
    -0.08
     जोर
    -0.08
     contempl
    -0.07
    ồ
    -0.07
    POSITIVE LOGITS
     Somehow
    0.09
     overcome
    0.09
    ?"
    0.09
     overcame
    0.09
    ？”
    0.09
     funktioniert
    0.08
     aparentemente
    0.08
    秘诀
    0.08
     convencer
    0.08
    rium
    0.08
    Activations Density 0.107%

    No Known Activations