© 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. 23-RESID-POST-AA
    11. 47954
    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    4
    -0.12
     four
    -0.12
    four
    -0.12
    四
    -0.11
    -four
    -0.11
     cuatro
    -0.11
    ４
    -0.11
     April
    -0.10
     ನಾಲ
    -0.10
    ৪
    -0.10
    POSITIVE LOGITS
    ング
    0.08
     grpc
    0.08
     revanche
    0.08
    .Le
    0.08
     bas
    0.08
    밍
    0.08
     rew
    0.08
    েস
    0.08
     resistente
    0.08
    OUS
    0.08
    Activations Density 0.019%

    No Known Activations