© 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. 7-RESID-POST-AA
    11. 1168
    Prev
    Next
    INDEX
    Explanations

    woman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     delin
    -0.08
     substitute
    -0.08
    /tr
    -0.07
    ajan
    -0.07
     sugars
    -0.07
     Lone
    -0.07
     loci
    -0.07
     locus
    -0.07
     substitutes
    -0.07
    心经
    -0.07
    POSITIVE LOGITS
     이번
    0.08
     चम
    0.08
     cheating
    0.08
     교수
    0.07
     viva
    0.07
     ér
    0.07
     cheval
    0.07
     Professor
    0.07
     pard
    0.07
     medd
    0.07
    Activations Density 0.060%

    No Known Activations