© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16655
    Prev
    Next
    INDEX
    Explanations

    ROS related

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antiviral
    -0.11
    Ansi
    -0.11
    Emoji
    -0.11
    .cloudflare
    -0.10
     rebellious
    -0.10
    @yahoo
    -0.10
     Promotional
    -0.10
     prepaid
    -0.10
     SUBSTITUTE
    -0.09
     decadent
    -0.09
    POSITIVE LOGITS
    _pose
    0.15
    .pose
    0.14
     ROS
    0.13
     rospy
    0.12
     pose
    0.12
     traj
    0.12
     robotics
    0.12
    _robot
    0.12
    ROS
    0.12
    (robot
    0.12
    Activations Density 0.007%

    No Known Activations