© 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. 48012
    Prev
    Next
    INDEX
    Explanations

    Как

    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
    екте
    -0.08
    -mon
    -0.08
     cans
    -0.08
     GRAN
    -0.08
    clam
    -0.08
     Cous
    -0.08
     Giro
    -0.07
     yapan
    -0.07
    hac
    -0.07
    mon
    -0.07
    POSITIVE LOGITS
    ني
    0.09
     하면
    0.08
     будто
    0.08
     intim
    0.08
     determine
    0.08
     qilib
    0.07
    نف
    0.07
     حدوث
    0.07
    581
    0.07
    овы
    0.07
    Activations Density 0.011%

    No Known Activations