© 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. 789
    Prev
    Next
    INDEX
    Explanations

    inside

    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
    ovement
    -0.08
     टी
    -0.08
     enfoque
    -0.07
     evoc
    -0.07
     penelitian
    -0.07
     TE
    -0.07
     vý
    -0.07
     terdiri
    -0.07
    。例如
    -0.07
     sei
    -0.07
    POSITIVE LOGITS
     middag
    0.08
    ural
    0.08
    boat
    0.08
    pickle
    0.08
    /mail
    0.08
    Compare
    0.08
    =password
    0.08
     امروز
    0.08
    roc
    0.08
     goodwill
    0.08
    Activations Density 0.006%

    No Known Activations