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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54935
    Prev
    Next
    INDEX
    Explanations

    private

    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
     тяжел
    -0.08
     малень
    -0.08
    .urlencoded
    -0.08
     крем
    -0.08
     pueblos
    -0.07
     الصغيرة
    -0.07
    鹿
    -0.07
     entretanto
    -0.07
    (css
    -0.07
     pequeña
    -0.07
    POSITIVE LOGITS
    }->{
    0.08
     episodes
    0.08
     cycles
    0.08
    agem
    0.07
     prophecy
    0.07
     imitation
    0.07
    stes
    0.07
    ikho
    0.07
    raad
    0.07
     প্ৰত
    0.07
    Activations Density 0.001%

    No Known Activations