© 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. 19-RESID-POST-AA
    11. 103137
    Prev
    Next
    INDEX
    Explanations

    adults

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -0.09
     stessa
    -0.08
    which
    -0.08
     same
    -0.08
    使
    -0.08
     particular
    -0.07
    传统
    -0.07
     core
    -0.07
    unction
    -0.07
     main
    -0.07
    POSITIVE LOGITS
     discussing
    0.11
     Lorem
    0.10
     avoids
    0.10
     مشک
    0.10
     flirting
    0.09
     willingly
    0.09
     voluntarily
    0.09
    -focused
    0.09
     shouting
    0.09
     consenting
    0.09
    Activations Density 0.007%

    No Known Activations