© 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. 26066
    Prev
    Next
    INDEX
    Explanations

    Short periods of time

    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
     सुन
    -0.08
     koron
    -0.08
    Smoking
    -0.08
     dentes
    -0.08
     banho
    -0.08
     있었다
    -0.08
     dengue
    -0.08
     проис
    -0.08
     ఘటన
    -0.08
    Instance
    -0.07
    POSITIVE LOGITS
     expansión
    0.08
     expand
    0.08
     വിപ
    0.08
     expands
    0.08
     reducers
    0.08
     productividad
    0.08
     expansão
    0.08
     vasta
    0.08
     décennies
    0.08
     lengthy
    0.08
    Activations Density 0.005%

    No Known Activations