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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 21016
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ล่าสุด
    -0.08
     շարունակ
    -0.08
     ntej
    -0.08
     ნაბიჯ
    -0.08
    թաց
    -0.08
     cohesive
    -0.08
     cohesion
    -0.08
    ícies
    -0.08
    ызы
    -0.08
     กล่าวว่า
    -0.08
    POSITIVE LOGITS
     add
    0.12
    .add
    0.11
    +n
    0.10
     added
    0.10
     adding
    0.10
    添加
    0.10
    追加
    0.10
     adicion
    0.10
     offset
    0.10
     ajouter
    0.10
    Activations Density 0.006%

    No Known Activations