© 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. 15-RESID-POST-AA
    11. 16462
    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ileges
    -0.07
    langen
    -0.07
     obtain
    -0.07
     avoiding
    -0.07
    ಬಂಧ
    -0.07
     obt
    -0.07
     de
    -0.07
    ousine
    -0.07
     taim
    -0.07
     Orientierung
    -0.07
    POSITIVE LOGITS
     ✅
    0.12
     ✔
    0.10
     YES
    0.10
     Attempt
    0.09
    是否
    0.09
    (**
    0.09
    ✅
    0.09
     Attempts
    0.09
     attempted
    0.08
     käy
    0.08
    Activations Density 0.009%

    No Known Activations