Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43712
    Prev
    Next
    INDEX
    Explanations

    "then"

    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
     tendances
    -0.08
    .tags
    -0.07
     cousin
    -0.07
    Hot
    -0.07
    leren
    -0.07
     menit
    -0.07
    Modulo
    -0.07
     turbo
    -0.07
     modulo
    -0.07
    Neighbours
    -0.07
    POSITIVE LOGITS
     далее
    0.08
    quear
    0.08
     Далее
    0.08
     перечис
    0.08
    عراض
    0.08
     излож
    0.08
     objek
    0.08
    ovel
    0.08
     estip
    0.07
     erläut
    0.07
    Activations Density 0.030%

    No Known Activations