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. 65643
    Prev
    Next
    INDEX
    Explanations

    Code, math, and 3D drawings

    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
    .Broadcast
    -0.08
     Teresa
    -0.08
    avond
    -0.08
    .broadcast
    -0.08
     organize
    -0.08
     fasting
    -0.08
    .normalize
    -0.08
    ಕ್ತ
    -0.07
    iciente
    -0.07
    ichannel
    -0.07
    POSITIVE LOGITS
     dargest
    0.09
    simulate
    0.09
     dargestellt
    0.08
     photographed
    0.08
     blurred
    0.08
     illusion
    0.08
     angled
    0.08
     Viewed
    0.08
     portrayed
    0.08
     shading
    0.08
    Activations Density 0.007%

    No Known Activations