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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68838
    Prev
    Next
    INDEX
    Explanations

    .now

    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
    -choice
    -0.10
     القر
    -0.09
     ionic
    -0.08
    مد
    -0.07
     sik
    -0.07
     simp
    -0.07
     escolha
    -0.07
     garoto
    -0.07
     performances
    -0.07
     encoder
    -0.07
    POSITIVE LOGITS
    estr
    0.08
     metod
    0.07
     méth
    0.07
     Extr
    0.07
     shotgun
    0.07
    оз
    0.07
     Метод
    0.07
     వంటి
    0.07
    ేవ
    0.07
    otov
    0.07
    Activations Density 0.002%

    No Known Activations