© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 113147
    Prev
    Next
    INDEX
    Explanations

    inequalities

    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
     Baut
    -0.08
     സമ
    -0.08
     tandem
    -0.08
    editing
    -0.07
     Alvin
    -0.07
     gase
    -0.07
    ライブ
    -0.07
     Weiss
    -0.07
     Milton
    -0.07
     Ay
    -0.07
    POSITIVE LOGITS
     exert
    0.08
     pare
    0.08
     plateau
    0.07
     있
    0.07
     entr
    0.07
    нь
    0.07
     Emily
    0.07
     zufrieden
    0.07
    نده
    0.07
     Padres
    0.07
    Activations Density 0.028%

    No Known Activations