© 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. 26562
    Prev
    Next
    INDEX
    Explanations

    statistical

    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
     navy
    -0.08
     remarks
    -0.07
     aclar
    -0.07
    型号
    -0.07
     overseeing
    -0.07
    격
    -0.07
    ucun
    -0.07
    _ram
    -0.07
     Oil
    -0.07
     Armour
    -0.07
    POSITIVE LOGITS
     statistically
    0.10
    Patterns
    0.10
     correlations
    0.09
    _patterns
    0.09
     casamento
    0.09
     rew
    0.09
     statistical
    0.09
     probable
    0.09
     Mulheres
    0.08
     Associations
    0.08
    Activations Density 0.013%

    No Known Activations