© 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. 51724
    Prev
    Next
    INDEX
    Explanations

    ’aff

    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
     def
    -0.08
     Todd
    -0.07
     obituary
    -0.07
     anden
    -0.07
     Trends
    -0.07
    ன்றி
    -0.07
    .minus
    -0.07
     Kath
    -0.07
     ileri
    -0.07
    ndice
    -0.07
    POSITIVE LOGITS
    ect
    0.09
     되고
    0.09
    	do
    0.08
    做愛
    0.08
     коль
    0.08
    do
    0.07
    ênd
    0.07
    і
    0.07
    оро
    0.07
    ត
    0.07
    Activations Density 0.000%

    No Known Activations