© 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. 108735
    Prev
    Next
    INDEX
    Explanations

    masculine

    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
    Tat
    -0.08
     Tattoo
    -0.08
     alone
    -0.07
     wars
    -0.07
     WAS
    -0.07
    tat
    -0.07
     swims
    -0.07
     Tat
    -0.07
     smer
    -0.07
     psoriasis
    -0.07
    POSITIVE LOGITS
    mlink
    0.08
    깔
    0.08
     chóng
    0.08
     Daly
    0.08
    ുവരി
    0.08
    passt
    0.08
     schip
    0.08
    ाहित्य
    0.07
    issut
    0.07
    ich
    0.07
    Activations Density 0.002%

    No Known Activations