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. 112382
    Prev
    Next
    INDEX
    Explanations

    Century

    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
    ින්
    -0.08
     peanuts
    -0.08
     neur
    -0.08
    aké
    -0.07
     vec
    -0.07
     Φ
    -0.07
    edom
    -0.07
    袋
    -0.07
    bereiche
    -0.07
     আস
    -0.07
    POSITIVE LOGITS
    -speaking
    0.08
     Ly
    0.08
     Monsters
    0.08
    ительности
    0.08
    典
    0.08
    .ly
    0.08
     Ligne
    0.07
     poisonous
    0.07
     والس
    0.07
     waxing
    0.07
    Activations Density 0.018%

    No Known Activations