© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6622
    Prev
    Next
    INDEX
    Explanations

    Navigation, headings

    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
     wearable
    -0.08
     portability
    -0.08
     сант
    -0.08
     Employee
    -0.08
     Workers
    -0.08
     біл
    -0.08
    .employee
    -0.08
     мебель
    -0.08
     walks
    -0.08
     воспит
    -0.08
    POSITIVE LOGITS
     trajectory
    0.18
     koers
    0.17
    _course
    0.17
     maneuver
    0.17
     mane
    0.16
     course
    0.16
    course
    0.16
     trajetória
    0.16
    Course
    0.16
     heading
    0.16
    Activations Density 0.051%

    No Known Activations