© 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. 3-RESID-POST-AA
    11. 896
    Prev
    Next
    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     definite
    -0.10
    ​
    -0.08
     Zel
    -0.08
     agh
    -0.07
     villagers
    -0.07
    543
    -0.07
     bedrijf
    -0.07
    Ptr
    -0.07
     constituents
    -0.07
     بأ
    -0.07
    POSITIVE LOGITS
     hi
    0.09
    食
    0.08
     wo
    0.07
     Rivera
    0.07
    ুব
    0.07
     Tas
    0.07
     Bowen
    0.07
    足
    0.07
     Begins
    0.07
    介
    0.07
    Activations Density 0.002%

    No Known Activations