© 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. 63686
    Prev
    Next
    INDEX
    Explanations

    Primary/secondary colors

    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
     Naz
    -0.08
    jte
    -0.08
     famously
    -0.08
    431
    -0.08
     cadenas
    -0.07
    Naz
    -0.07
    Nada
    -0.07
     Nazi
    -0.07
    -0.07
    gbu
    -0.07
    POSITIVE LOGITS
     yaiku
    0.10
     nyaéta
    0.09
    -story
    0.09
    -ui
    0.08
     accent
    0.08
    -high
    0.08
    0.08
     playful
    0.08
    .secondary
    0.08
     عند
    0.07
    Activations Density 0.002%
    No Known Activations