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. 41967
    Prev
    Next
    INDEX
    Explanations

    also known as

    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
     touchscreen
    -0.08
     protr
    -0.08
     omvat
    -0.07
    கம்
    -0.07
     erzeug
    -0.07
    动作
    -0.07
    ande
    -0.07
     rapaz
    -0.07
     physic
    -0.07
     wireless
    -0.07
    POSITIVE LOGITS
     colo
    0.08
    .cid
    0.08
     faint
    0.08
     Rhine
    0.07
     cid
    0.07
     waterfalls
    0.07
    cid
    0.07
     Camino
    0.07
     পথে
    0.07
     União
    0.07
    Activations Density 0.020%

    No Known Activations