© 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. 91422
    Prev
    Next
    INDEX
    Explanations

    hormones

    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
     footing
    -0.08
     drawers
    -0.08
     asylum
    -0.08
     ermee
    -0.08
    foot
    -0.08
     სა�
    -0.08
     manual
    -0.07
     belongings
    -0.07
     participants
    -0.07
    oped
    -0.07
    POSITIVE LOGITS
     hormones
    0.12
     regulating
    0.12
     regulates
    0.11
     Produced
    0.10
     Horm
    0.10
     горм
    0.10
     regulate
    0.10
    Produced
    0.09
     cannabinoids
    0.09
     produced
    0.09
    Activations Density 0.014%

    No Known Activations