© 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. 16388
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

    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
     Gw
    -0.08
    éd
    -0.08
    در
    -0.08
    
    -0.08
    andan
    -0.08
     Luka
    -0.08
    éier
    -0.07
     Libre
    -0.07
     Ilo
    -0.07
     rehefa
    -0.07
    POSITIVE LOGITS
    versible
    0.08
     forbidden
    0.08
    Forbidden
    0.08
    vers
    0.07
    div
    0.07
     кеп
    0.07
    972
    0.07
     keinerlei
    0.07
    772
    0.07
     dall
    0.07
    Activations Density 0.001%

    No Known Activations