© 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. 44666
    Prev
    Next
    INDEX
    Explanations

    Choosing

    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
     awk
    -0.09
     vors
    -0.08
     beil
    -0.08
     består
    -0.07
     Hok
    -0.07
    -0.07
     eff
    -0.07
    �
    -0.07
     perceive
    -0.07
     KW
    -0.07
    POSITIVE LOGITS
     wählen
    0.11
     tercih
    0.10
     선택
    0.10
    选择
    0.09
     choice
    0.09
     выбира
    0.09
    Choice
    0.09
     pilihan
    0.09
     scelta
    0.09
    choice
    0.08
    Activations Density 0.044%
    No Known Activations