© 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. 64885
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     embarking
    -0.08
     outreach
    -0.07
    Achievement
    -0.07
     фил
    -0.07
    782
    -0.07
    梨
    -0.07
    。また
    -0.07
    -standard
    -0.07
    imized
    -0.07
     фл
    -0.07
    POSITIVE LOGITS
     לבין
    0.08
    izando
    0.08
    EMA
    0.07
     sexes
    0.07
    -ish
    0.07
    doch
    0.07
    hat
    0.07
     genders
    0.07
     cuz
    0.07
     passions
    0.07
    Activations Density 0.014%

    No Known Activations