© 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. 8008
    Prev
    Next
    INDEX
    Explanations

    结合

    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
    Grund
    -0.08
     Probate
    -0.08
     PSI
    -0.08
     Grund
    -0.08
    -profit
    -0.08
     ganger
    -0.08
    -place
    -0.07
     Grunde
    -0.07
     nein
    -0.07
     psi
    -0.07
    POSITIVE LOGITS
     futuristic
    0.09
     interdisciplinary
    0.09
     multidisciplinary
    0.08
     interdiscip
    0.08
     SQL
    0.08
     creatively
    0.08
     actionable
    0.08
     synthes
    0.08
     SWOT
    0.08
     imaginative
    0.08
    Activations Density 0.002%

    No Known Activations