© 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. 2885
    Prev
    Next
    INDEX
    Explanations

    selection

    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
     Sierra
    -0.08
    .W
    -0.08
     stomach
    -0.08
    	W
    -0.08
    WM
    -0.07
    88
    -0.07
    ,W
    -0.07
     bovenstaande
    -0.07
     వార
    -0.07
    edza
    -0.07
    POSITIVE LOGITS
     fø
    0.09
     tek
    0.08
    _udp
    0.07
     fug
    0.07
     Spawn
    0.07
    _cmd
    0.07
     disput
    0.07
    �
    0.07
    靠
    0.07
     Shame
    0.07
    Activations Density 0.006%

    No Known Activations