© 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. 52214
    Prev
    Next
    INDEX
    Explanations

    Turkish 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
    қа
    -0.09
    ılıb
    -0.09
    елю
    -0.08
    .ph
    -0.08
    etto
    -0.08
    qata
    -0.08
    sete
    -0.08
    قا
    -0.08
    �
    -0.08
    orts
    -0.07
    POSITIVE LOGITS
    ştir
    0.14
    mesine
    0.13
    şt
    0.13
     ilgili
    0.13
     birlikte
    0.11
    ýin
    0.11
    yiş
    0.11
    meden
    0.11
    mesini
    0.10
    mede
    0.10
    Activations Density 0.002%

    No Known Activations