© 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. 96832
    Prev
    Next
    INDEX
    Explanations

    attention

    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
    'installation
    -0.09
     poop
    -0.09
     you'll
    -0.09
     माल
    -0.09
     massif
    -0.08
     mathematics
    -0.08
     freeware
    -0.08
     gotta
    -0.08
     tomorrow
    -0.08
     uptime
    -0.08
    POSITIVE LOGITS
     Attention
    0.16
    Attention
    0.16
    _attention
    0.16
     attention
    0.16
     supervision
    0.15
    attention
    0.15
     supervise
    0.14
     guidance
    0.14
     guided
    0.14
     supervising
    0.13
    Activations Density 0.043%

    No Known Activations