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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6149
    Prev
    Next
    INDEX
    Explanations

    intervals or sprints

    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
     peaceful
    -0.10
     안정
    -0.09
     reassuring
    -0.09
     comfy
    -0.09
    舒
    -0.09
    稳定
    -0.08
     tranquilo
    -0.08
     stabile
    -0.08
     melancholy
    -0.08
     strolling
    -0.08
    POSITIVE LOGITS
     интерв
    0.17
     Tab
    0.16
     intervals
    0.16
     sprint
    0.16
     interval
    0.15
    Interval
    0.15
     Interval
    0.15
    Tab
    0.14
     Sprint
    0.14
    _INTERVAL
    0.14
    Activations Density 0.017%

    No Known Activations