© 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 EvalsExportsinterp-engineNEWAPI 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. 110502
    Prev
    Next
    INDEX
    Explanations

    SIM card

    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
     '+'
    -0.09
     framing
    -0.08
     '.'
    -0.08
     dign
    -0.08
     weaker
    -0.07
     DRM
    -0.07
     qual
    -0.07
    /fr
    -0.07
    欣
    -0.07
     formul
    -0.07
    POSITIVE LOGITS
     havoc
    0.08
    ická
    0.08
     adéqu
    0.08
     Hoc
    0.08
    americana
    0.08
    Hola
    0.08
     graines
    0.08
     économ
    0.07
     instantiated
    0.07
    ಿಯಾಗ
    0.07
    Activations Density 0.003%

    No Known Activations