© 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. 113637
    Prev
    Next
    INDEX
    Explanations

    Thomas

    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
    tpl
    -0.08
    irman
    -0.08
    march
    -0.08
     hm
    -0.07
    姜
    -0.07
     Dwight
    -0.07
     transl
    -0.07
     pregnant
    -0.07
     words
    -0.07
     ballistic
    -0.07
    POSITIVE LOGITS
     يعد
    0.08
     Implements
    0.08
     يع
    0.08
    ก
    0.08
    <Property
    0.07
     bezit
    0.07
    നിയ
    0.07
     із
    0.07
    <com
    0.07
     tien
    0.07
    Activations Density 0.001%

    No Known Activations