© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103190
    Prev
    Next
    INDEX
    Explanations

    say number 3

    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
     kakhulu
    -0.09
    亿
    -0.08
     billions
    -0.08
     remuner
    -0.08
    	kfree
    -0.08
     lifelong
    -0.08
    ugut
    -0.08
    _setopt
    -0.08
     ngokup
    -0.08
    enua
    -0.08
    POSITIVE LOGITS
     arranged
    0.13
     Arrangement
    0.12
    排列
    0.12
     arranging
    0.12
     arrangement
    0.11
     Arrange
    0.11
    Arrangement
    0.11
     arrange
    0.11
    布局
    0.10
     grids
    0.10
    Activations Density 0.010%

    No Known Activations