© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 68305
    Prev
    Next
    INDEX
    Explanations

    境

    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
     spe
    -0.08
     famili
    -0.08
    semester
    -0.08
    Spe
    -0.08
    pe
    -0.07
    iture
    -0.07
     দেখ
    -0.07
    IV
    -0.07
    gue
    -0.07
    itures
    -0.07
    POSITIVE LOGITS
     trả
    0.10
     anb
    0.08
     ANI
    0.08
    税
    0.08
     fintech
    0.08
     oficialmente
    0.08
     aanbieden
    0.08
    手续
    0.08
     व्यापार
    0.08
     aik
    0.08
    Activations Density 0.003%

    No Known Activations