© 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. 30097
    Prev
    Next
    INDEX
    Explanations

    memory leak

    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
    陆
    -0.08
    _dec
    -0.08
     wür
    -0.08
     saanud
    -0.08
    European
    -0.08
     stär
    -0.08
    -Afr
    -0.08
     बोले
    -0.08
    (face
    -0.08
     rugged
    -0.08
    POSITIVE LOGITS
     leaks
    0.13
    垃圾
    0.12
     garbage
    0.12
    .memory
    0.12
     Garbage
    0.12
    Leaks
    0.12
     bugs
    0.11
     leak
    0.11
     déchets
    0.11
     desperd
    0.11
    Activations Density 0.007%

    No Known Activations