© 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. 23-RESID-POST-AA
    11. 5518
    Prev
    Next
    INDEX
    Explanations

    5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opause
    -0.08
     recul
    -0.08
    stum
    -0.08
     patio
    -0.08
     patios
    -0.08
    (Animation
    -0.08
    (BASE
    -0.08
     courtyard
    -0.08
    863
    -0.08
     reflex
    -0.07
    POSITIVE LOGITS
     kg
    0.14
    kg
    0.13
     bara
    0.13
    公斤
    0.12
     Kg
    0.12
     ബ
    0.11
     кг
    0.11
     ਬ
    0.11
     బ
    0.11
     ಬ
    0.10
    Activations Density 0.001%

    No Known Activations