© 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. 25883
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     долж
    -0.09
    Fuse
    -0.08
    .offset
    -0.08
    ро
    -0.08
    Dispose
    -0.08
    (offset
    -0.08
    Tone
    -0.07
    .one
    -0.07
     divisions
    -0.07
    넷
    -0.07
    POSITIVE LOGITS
     maximizing
    0.14
     maximize
    0.12
    maximize
    0.11
     maxim
    0.11
     terbaik
    0.10
     monoton
    0.10
     Maxim
    0.10
     ఉత్త
    0.09
     Optimal
    0.09
     optimal
    0.09
    Activations Density 0.025%

    No Known Activations