© 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. 29445
    Prev
    Next
    INDEX
    Explanations

    skills

    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
    IMAL
    -0.08
    Creating
    -0.08
    NST
    -0.08
     બનાવવા
    -0.08
     cie
    -0.07
     suisse
    -0.07
    Address
    -0.07
    VAT
    -0.07
     NST
    -0.07
     olu
    -0.07
    POSITIVE LOGITS
     disclaim
    0.09
     వెల్లడ
    0.09
     disposição
    0.09
    mention
    0.08
     mencionar
    0.08
     ప్రకట
    0.08
     pertinentes
    0.08
     mentioning
    0.08
     শেষে
    0.08
     Horse
    0.08
    Activations Density 0.004%

    No Known Activations