© 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. 19-RESID-POST-AA
    11. 103277
    Prev
    Next
    INDEX
    Explanations

    |

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behave
    -0.09
     and
    -0.09
     ולה
    -0.09
     μπορούν
    -0.09
     וכל
    -0.09
    能够
    -0.09
     orice
    -0.09
     cualquier
    -0.08
     to
    -0.08
     любые
    -0.08
    POSITIVE LOGITS
     insufficient
    0.16
     Incorrect
    0.15
     incorrect
    0.15
     terlalu
    0.14
     verkeerde
    0.14
     inadequate
    0.14
     wrong
    0.14
    wrong
    0.14
    Incorrect
    0.14
     onvoldoende
    0.13
    Activations Density 0.012%

    No Known Activations