© 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. 75830
    Prev
    Next
    INDEX
    Explanations

    Russian text

    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
    again
    -0.08
    קע
    -0.08
     gewen
    -0.08
    iyy
    -0.08
    aissez
    -0.08
    -abkhazia
    -0.07
    -0.07
     passada
    -0.07
     unavoidable
    -0.07
    Vpc
    -0.07
    POSITIVE LOGITS
     Gradient
    0.09
     engra
    0.09
     Jump
    0.08
     parody
    0.08
    Ам
    0.08
    Playing
    0.08
     Am
    0.08
     amusing
    0.08
     Playing
    0.08
     عمد
    0.08
    Activations Density 0.001%
    No Known Activations