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. 52703
    Prev
    Next
    INDEX
    Explanations

    hoa

    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
     colleg
    -0.09
    urgeon
    -0.08
    /**
    -0.07
    жу
    -0.07
    ковод
    -0.07
     atop
    -0.07
    -0.07
     employ
    -0.07
    ราย
    -0.07
     interna
    -0.07
    POSITIVE LOGITS
     Rwanda
    0.08
     લીધ
    0.08
     reflected
    0.07
     соответствии
    0.07
     VIN
    0.07
    QRSTUVWXYZ
    0.07
     bary
    0.07
     EV
    0.07
    >A
    0.07
     þur
    0.07
    Activations Density 0.001%

    No Known Activations