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. 58363
    Prev
    Next
    INDEX
    Explanations

    0

    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
     plasm
    -0.08
     literal
    -0.08
     geheim
    -0.08
     Lambert
    -0.07
    ouse
    -0.07
     Johns
    -0.07
     Taus
    -0.07
    geant
    -0.07
    deel
    -0.07
    -0.07
    POSITIVE LOGITS
    规格
    0.09
     Display
    0.08
     شاشة
    0.08
     telas
    0.08
    采取
    0.08
    ΗΣ
    0.08
    178
    0.08
     MED
    0.08
    MED
    0.08
     تحتاج
    0.08
    Activations Density 0.005%

    No Known Activations