© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54319
    Prev
    Next
    INDEX
    Explanations

    tyr

    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
    indruck
    -0.08
     Tah
    -0.08
     Horizon
    -0.07
    zahl
    -0.07
     rur
    -0.07
     Sense
    -0.07
    Tau
    -0.07
    踏
    -0.07
    ността
    -0.07
     Tau
    -0.07
    POSITIVE LOGITS
     sév
    0.08
     لف
    0.07
     force
    0.07
    務
    0.07
     veille
    0.07
    amental
    0.07
     Brock
    0.07
    fle
    0.07
     تمام
    0.07
     presidency
    0.07
    Activations Density 0.004%

    No Known Activations