© 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. 13397
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
     ലീ
    -0.08
    _LE
    -0.08
     isl
    -0.07
     специал
    -0.07
     ausge
    -0.07
    ydro
    -0.07
     vär
    -0.07
     ис
    -0.07
     указан
    -0.07
     связан
    -0.07
    POSITIVE LOGITS
     sunny
    0.07
    unan
    0.07
    TP
    0.07
     Eld
    0.07
    tp
    0.07
    ighbor
    0.07
     xuống
    0.07
    날
    0.07
     Ar
    0.07
     olem
    0.07
    Activations Density 0.013%

    No Known Activations