© 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. 69955
    Prev
    Next
    INDEX
    Explanations

    }{

    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
     حال
    -0.09
    =-=-
    -0.09
     Hoover
    -0.08
    SH
    -0.08
    istine
    -0.08
    KW
    -0.08
    ಾಂತರ
    -0.08
    SELF
    -0.08
    akh
    -0.08
     horses
    -0.08
    POSITIVE LOGITS
     legitimately
    0.08
    combe
    0.07
     Ple
    0.07
     �
    0.07
     simplifies
    0.07
     demand
    0.07
     Lös
    0.07
     sof
    0.07
     wel
    0.07
    cd
    0.07
    Activations Density 0.124%

    No Known Activations