© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 103480
    Prev
    Next
    INDEX
    Explanations

    failed

    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
     يظهر
    -0.09
    -↵↵
    -0.09
    
    -0.09
     [+]↵↵
    -0.08
     presentan
    -0.08
     betere
    -0.08
     және
    -0.08
    -/
    -0.08
    :↵↵
    -0.08
     designed
    -0.08
    POSITIVE LOGITS
    怎么办
    0.08
     controlar
    0.07
     tentang
    0.07
    ())[
    0.07
     fate
    0.07
    olarmente
    0.07
    0.07
     Kit
    0.07
     zama
    0.07
     %
    0.07
    Activations Density 0.000%

    No Known Activations