© 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. 69712
    Prev
    Next
    INDEX
    Explanations

    arrangements of items

    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
    порт
    -0.08
     Pen
    -0.07
     sammen
    -0.07
    si
    -0.07
     vital
    -0.07
     stacked
    -0.07
     comprehensive
    -0.07
    ovar
    -0.07
     stacking
    -0.07
     supervised
    -0.07
    POSITIVE LOGITS
     ọgụ
    0.09
     Rover
    0.08
    Businesses
    0.08
     Businesses
    0.08
    -cols
    0.07
    urende
    0.07
    Lux
    0.07
     businesses
    0.07
    anthemums
    0.07
     Realtor
    0.07
    Activations Density 0.019%

    No Known Activations