© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102453
    Prev
    Next
    INDEX
    Explanations

    say ":"

    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
     გამოიყენ
    -0.11
    usebenzisa
    -0.10
     ýaly
    -0.10
     არსებული
    -0.10
     кеүек
    -0.09
     გამოყენ
    -0.09
     tirhisa
    -0.09
     hoʻohana
    -0.09
     истифода
    -0.09
     ನಡೆದಿದೆ
    -0.09
    POSITIVE LOGITS
    :a
    0.14
    :N
    0.14
    :?
    0.13
    :n
    0.13
    }:{
    0.13
    :%
    0.13
    :j
    0.13
    :k
    0.13
    :l
    0.13
    :b
    0.13
    Activations Density 0.014%

    No Known Activations