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. 77532
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
     Nulla
    -0.08
    åk
    -0.08
    ủ
    -0.08
     უკ
    -0.07
     لک
    -0.07
    ამბ
    -0.07
    აუბ
    -0.07
     gegn
    -0.07
    bonne
    -0.07
     каршы
    -0.07
    POSITIVE LOGITS
     Roz
    0.08
     исполнитель
    0.08
     Plan
    0.07
     systematically
    0.07
     नियमित
    0.07
     Alice
    0.07
     предлож
    0.07
     использ
    0.07
    Chu
    0.07
     araştır
    0.07
    Activations Density 0.000%

    No Known Activations