© 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. 23-RESID-POST-AA
    11. 52148
    Prev
    Next
    INDEX
    Explanations

    Russian language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    езды
    -0.08
     Literatur
    -0.08
    axes
    -0.08
     أجزاء
    -0.08
     depiction
    -0.08
    ridden
    -0.08
    rying
    -0.08
    хід
    -0.08
    റി
    -0.07
    Lak
    -0.07
    POSITIVE LOGITS
     велич
    0.10
     μεγαλ
    0.10
     волн
    0.10
     вид
    0.09
     великолеп
    0.09
     настро
    0.09
     удив
    0.09
     могу
    0.09
     existir
    0.09
     мастер
    0.09
    Activations Density 0.009%

    No Known Activations