© 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. 45505
    Prev
    Next
    INDEX
    Explanations

    flower arrangements

    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
     દ્વ
    -0.09
     dadurch
    -0.08
     elektronische
    -0.08
     checkpoints
    -0.08
     tinnitus
    -0.08
     register
    -0.08
     exercício
    -0.08
    lags
    -0.08
     audi
    -0.08
     электрон
    -0.08
    POSITIVE LOGITS
     florist
    0.13
     floral
    0.12
     flowers
    0.12
     फूल
    0.11
     flower
    0.11
     fraî
    0.10
     petals
    0.10
     greenery
    0.10
     bloemen
    0.10
     Floral
    0.10
    Activations Density 0.030%

    No Known Activations