© 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. 23-RESID-POST-AA
    11. 50911
    Prev
    Next
    INDEX
    Explanations

    Indian festivals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -write
    -0.08
     Ph
    -0.08
    -remove
    -0.08
    Remove
    -0.08
    REMOVE
    -0.08
     Folding
    -0.08
    기도
    -0.08
     GEL
    -0.07
    usable
    -0.07
     szer
    -0.07
    POSITIVE LOGITS
    ano
    0.08
    疫情
    0.08
    ាន
    0.08
     बढ़
    0.08
    êng
    0.08
    ewerk
    0.08
    ҳо
    0.08
    àm
    0.08
    èn
    0.07
    ews
    0.07
    Activations Density 0.000%

    No Known Activations