© 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. 23-RESID-POST-AA
    6. 97878
    Prev
    Next
    INDEX
    Explanations

    прав

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ুভ
    -0.08
    ㅇ
    -0.08
    ава
    -0.07
     }}>{
    -0.07
    ítő
    -0.07
    heids
    -0.07
     %@",
    -0.07
    날
    -0.07
    aknya
    -0.07
     oeste
    -0.07
    POSITIVE LOGITS
    ками
    0.09
    ки
    0.08
    кой
    0.08
    chains
    0.08
    -grey
    0.08
     Creme
    0.07
    ках
    0.07
     Dynamic
    0.07
     linking
    0.07
    кою
    0.07
    Activations Density 0.001%

    No Known Activations