© 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. 19-RESID-POST-AA
    11. 18791
    Prev
    Next
    INDEX
    Explanations

    style

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vestibulum
    -0.08
    istream
    -0.08
    -perfect
    -0.08
    procedure
    -0.08
    instantiate
    -0.08
     নির্ব
    -0.07
    896
    -0.07
     procedure
    -0.07
    soa
    -0.07
    ofstream
    -0.07
    POSITIVE LOGITS
    =https
    0.09
     或
    0.09
    =''↵
    0.09
    =False
    0.09
     如果
    0.08
    =\
    0.08
    ↵
↵
    0.08
     или
    0.08
    ’↵
    0.08
    =''
    0.08
    Activations Density 0.001%

    No Known Activations