© 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. 867
    Prev
    Next
    INDEX
    Explanations

    ###

    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
    。这
    -0.08
     пит
    -0.08
     psychotherapy
    -0.08
     proclaim
    -0.08
     intending
    -0.07
     preaching
    -0.07
     прол
    -0.07
    拥
    -0.07
     spectacle
    -0.07
     bp
    -0.07
    POSITIVE LOGITS
     computations
    0.11
     Determine
    0.10
     먼저
    0.10
     بررسی
    0.09
     tricky
    0.08
     Calculation
    0.08
     चरण
    0.08
    Compute
    0.08
     gcd
    0.08
     Compute
    0.08
    Activations Density 0.018%

    No Known Activations