© 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. 3-RESID-POST-AA
    11. 13055
    Prev
    Next
    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Oak
    -0.09
    Synopsis
    -0.08
     өз
    -0.08
     narrated
    -0.08
    Tips
    -0.08
    lear
    -0.07
     concierge
    -0.07
    Ar
    -0.07
    Cab
    -0.07
    VP
    -0.07
    POSITIVE LOGITS
     ausgeschlossen
    0.08
     вв
    0.08
     iter
    0.08
     pagal
    0.08
     minima
    0.08
     gcd
    0.08
    lā
    0.07
     सेवन
    0.07
     ht
    0.07
     cds
    0.07
    Activations Density 0.005%

    No Known Activations