© 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. 44465
    Prev
    Next
    INDEX
    Explanations

    action

    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
    균
    -0.08
     dominating
    -0.08
    Meth
    -0.07
     impur
    -0.07
    .account
    -0.07
    account
    -0.07
     account
    -0.07
     kolem
    -0.07
     sectional
    -0.07
     సామ
    -0.07
    POSITIVE LOGITS
     Aktionen
    0.10
     acciones
    0.09
     intervención
    0.09
     tindakan
    0.09
    处罚
    0.09
     कार्रवाई
    0.08
     действие
    0.08
    ’action
    0.08
     કાર્યવાહી
    0.08
     നടപടി
    0.08
    Activations Density 0.008%

    No Known Activations