Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98460
    Prev
    Next
    INDEX
    Explanations

    bots

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ächen
    -0.09
     transformative
    -0.09
     wrought
    -0.09
    Genres
    -0.08
     diagnoses
    -0.08
    ímetros
    -0.08
    iceáil
    -0.07
    צי
    -0.07
     exhort
    -0.07
     Cornwall
    -0.07
    POSITIVE LOGITS
     bots
    0.10
    _poll
    0.09
     BOT
    0.09
     Drone
    0.09
    机器人
    0.09
    (block
    0.09
     Bot
    0.09
     backlog
    0.09
    (bot
    0.09
    _interval
    0.08
    Activations Density 0.001%

    No Known Activations