© 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. 8191
    Prev
    Next
    INDEX
    Explanations

    electrical breakdown, arcing

    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
     museo
    -0.09
     peace
    -0.09
     contempl
    -0.09
     goodbye
    -0.08
     muse
    -0.08
    peace
    -0.08
     प्रय
    -0.08
     Peace
    -0.08
     newer
    -0.08
     contemplate
    -0.08
    POSITIVE LOGITS
     catastrophic
    0.09
     runaway
    0.09
    Inst
    0.08
    .Instant
    0.08
    Driver
    0.08
    瞬
    0.08
    股
    0.08
     Located
    0.08
     ignition
    0.08
     instantaneous
    0.08
    Activations Density 0.005%

    No Known Activations