© 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. 129500
    Prev
    Next
    INDEX
    Explanations

    analytic

    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
     travelling
    -0.07
    834
    -0.07
     വീണ്ടും
    -0.07
     peculiar
    -0.07
     missed
    -0.07
    ump
    -0.07
     говор
    -0.07
     confirmation
    -0.07
    debug
    -0.07
    ål
    -0.06
    POSITIVE LOGITS
     Chang
    0.08
    .metric
    0.08
     imprint
    0.08
     ervoor
    0.08
    obl
    0.08
     ঘোষ
    0.07
     huish
    0.07
     tillsammans
    0.07
     legalization
    0.07
    icits
    0.07
    Activations Density 0.000%

    No Known Activations