© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 109986
    Prev
    Next
    INDEX
    Explanations

    fear

    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
    Negative Logits
    验
    -0.08
    有所
    -0.08
    Tit
    -0.08
     акку
    -0.08
    Preferences
    -0.08
     जिम्म
    -0.08
     يبحث
    -0.08
     préfér
    -0.08
     qay
    -0.08
    满意
    -0.08
    POSITIVE LOGITS
     danach
    0.08
     Invoke
    0.07
     Brazilian
    0.07
     полот
    0.07
     та
    0.07
     impactos
    0.07
     obes
    0.07
     pandem
    0.07
     Deliver
    0.07
     obra
    0.07
    Activations Density 0.012%

    No Known Activations