© 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. 30855
    Prev
    Next
    INDEX
    Explanations

    of

    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
     படம்
    -0.09
     ചിത്രം
    -0.08
     Rechnung
    -0.08
     suatu
    -0.08
     എന്ന്
    -0.08
    ，会
    -0.07
    Outer
    -0.07
     ஆனால்
    -0.07
     போது
    -0.07
     સારવાર
    -0.07
    POSITIVE LOGITS
     Merr
    0.08
     interconnected
    0.08
     divis
    0.08
     состоя
    0.08
    Dx
    0.07
    ep
    0.07
    vip
    0.07
     действий
    0.07
    0.07
     действия
    0.07
    Activations Density 0.097%
    No Known Activations