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

    Neuronpedia

    Jacobian LensNEW
    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. 63770
    Prev
    Next
    INDEX
    Explanations

    morning stiffness

    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
     aest
    -0.09
     Pase
    -0.08
     வைத்த
    -0.08
     landscaped
    -0.08
     ठेव
    -0.08
     aesthetic
    -0.07
     festivities
    -0.07
     festive
    -0.07
    (Key
    -0.07
     रख
    -0.07
    POSITIVE LOGITS
    crip
    0.09
    晨
    0.08
    leş
    0.08
    odo
    0.08
    粒
    0.08
     hemisphere
    0.08
     plagued
    0.07
     morgens
    0.07
    erit
    0.07
    ling
    0.07
    Activations Density 0.003%

    No Known Activations