© 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. 30335
    Prev
    Next
    INDEX
    Explanations

    detergent

    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
    Api
    -0.08
     ge
    -0.08
    aviour
    -0.07
     Lob
    -0.07
     indicated
    -0.07
    percent
    -0.07
    259
    -0.07
     व्य
    -0.07
     lazer
    -0.07
     clock
    -0.07
    POSITIVE LOGITS
    =my
    0.09
    מון
    0.09
     deterg
    0.08
     preservatives
    0.08
     detergent
    0.08
     خلي
    0.08
     sulfate
    0.08
     aans
    0.08
     Renaissance
    0.08
    .vec
    0.07
    Activations Density 0.002%

    No Known Activations