© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 78057
    Prev
    Next
    INDEX
    Explanations

    circadian rhythms

    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
     mãos
    -0.09
     tabletop
    -0.09
     وسائل
    -0.09
     মাধ্যম
    -0.08
     refundable
    -0.08
    硕
    -0.08
     plush
    -0.08
    oteric
    -0.08
     nephew
    -0.08
     ballots
    -0.08
    POSITIVE LOGITS
     rhythms
    0.13
     cortisol
    0.11
     hormon
    0.11
     noct
    0.10
     rhythm
    0.10
    凌晨
    0.10
     горм
    0.10
     sincron
    0.10
     ryt
    0.10
    _clock
    0.10
    Activations Density 0.010%

    No Known Activations