© 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. 881
    Prev
    Next
    INDEX
    Explanations

    ede

    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
    -May
    -0.07
     Fiction
    -0.07
     matar
    -0.07
    dry
    -0.07
    uhay
    -0.07
     الأشخاص
    -0.07
    angled
    -0.07
    .ins
    -0.07
    isal
    -0.07
     встр
    -0.07
    POSITIVE LOGITS
     relinqu
    0.11
     уступ
    0.10
     conces
    0.09
     prostor
    0.09
     voluntarily
    0.09
     dearly
    0.08
     concessions
    0.08
     forfe
    0.08
     willingly
    0.08
     জায়গ
    0.08
    Activations Density 0.023%

    No Known Activations