© 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. 11-RESID-POST-AA
    11. 124
    Prev
    Next
    INDEX
    Explanations

    metabolic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Qualified
    -0.09
     pastoral
    -0.08
    _IRQHandler
    -0.08
     qualification
    -0.08
     infrastrukt
    -0.08
    _STACK
    -0.08
     hoops
    -0.08
    -stack
    -0.08
    -End
    -0.08
    -qualified
    -0.08
    POSITIVE LOGITS
     metabolism
    0.09
     गति
    0.09
     crunch
    0.08
     jobs
    0.08
    -paced
    0.08
    activity
    0.08
     riz
    0.08
     household
    0.08
     metabolismo
    0.08
     calculation
    0.08
    Activations Density 0.004%

    No Known Activations