© 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. 48017
    Prev
    Next
    INDEX
    Explanations

    IEEE publications

    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
     statewide
    -0.10
    Hence
    -0.09
    enum
    -0.08
    ылып
    -0.08
     discontinue
    -0.08
    retry
    -0.08
    Bonus
    -0.08
    ырып
    -0.08
    Footer
    -0.08
    Stat
    -0.07
    POSITIVE LOGITS
     consumers
    0.11
     Consumer
    0.11
     Depend
    0.11
     Industrial
    0.11
     Neural
    0.10
     Components
    0.10
     Instrument
    0.10
     Evolution
    0.09
     Consumers
    0.09
     Services
    0.09
    Activations Density 0.001%

    No Known Activations