© 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. 1064
    Prev
    Next
    INDEX
    Explanations

    /data

    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
     beauty
    -0.08
     connective
    -0.08
     repositories
    -0.07
     Riley
    -0.07
     lecture
    -0.07
     Koh
    -0.07
    生
    -0.07
     belleza
    -0.07
     noted
    -0.07
     hait
    -0.07
    POSITIVE LOGITS
     blew
    0.09
     ছিল
    0.09
    UAGE
    0.08
     blows
    0.08
    powers
    0.08
    Proc
    0.07
     disa
    0.07
    UNC
    0.07
    iseerde
    0.07
     blowing
    0.07
    Activations Density 0.000%

    No Known Activations