© 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. 3-RESID-POST-AA
    11. 2888
    Prev
    Next
    INDEX
    Explanations

    text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     குறிப்ப
    -0.08
    .app
    -0.08
     embarking
    -0.07
    ddd
    -0.07
     verfügt
    -0.07
     indul
    -0.07
     밝
    -0.07
    .check
    -0.07
     진
    -0.07
    ką
    -0.07
    POSITIVE LOGITS
    elier
    0.08
    -cli
    0.08
    CLI
    0.08
    ուղ
    0.08
    -ended
    0.08
    Таким
    0.08
    guns
    0.08
    -ln
    0.07
    ziehen
    0.07
     sujetos
    0.07
    Activations Density 0.000%

    No Known Activations