© 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. 95339
    Prev
    Next
    INDEX
    Explanations

    project

    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
     memset
    -0.08
     ön
    -0.08
    eiro
    -0.08
    研发
    -0.08
     دو
    -0.08
     сом
    -0.08
     oyster
    -0.08
     bảo
    -0.07
     duration
    -0.07
     hes
    -0.07
    POSITIVE LOGITS
    -plane
    0.09
    -away
    0.09
    ogr
    0.08
     techniek
    0.08
    plane
    0.08
    'Est
    0.08
     perpendicular
    0.08
    atories
    0.08
    ienne
    0.08
     parall
    0.08
    Activations Density 0.002%

    No Known Activations