© 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. 680
    Prev
    Next
    INDEX
    Explanations

    -part

    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
     thriving
    -0.08
     প্রচ
    -0.08
     sendiri
    -0.08
     thrive
    -0.08
     puerto
    -0.07
    رد
    -0.07
     रहने
    -0.07
     राहत
    -0.07
    awi
    -0.07
     countless
    -0.07
    POSITIVE LOGITS
     tasks
    0.10
     sequential
    0.09
     задачи
    0.08
     Solve
    0.08
     Parts
    0.08
     ഭാഗ
    0.08
     (§
    0.08
    三个
    0.08
    Firstly
    0.08
     начиная
    0.08
    Activations Density 0.016%

    No Known Activations