© 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. 19-RESID-POST-AA
    11. 102679
    Prev
    Next
    INDEX
    Explanations

    busyness

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     punitive
    -0.09
     προστα
    -0.09
     proteção
    -0.08
    remaining
    -0.08
     revenge
    -0.08
     extremist
    -0.08
     предус
    -0.08
     уничтож
    -0.08
     precaution
    -0.07
    consult
    -0.07
    POSITIVE LOGITS
     bustling
    0.36
     bustle
    0.29
     lively
    0.26
     vibrant
    0.23
     hustle
    0.23
     hectic
    0.22
     busy
    0.21
    忙
    0.21
     ramai
    0.20
    繁
    0.20
    Activations Density 0.057%

    No Known Activations