© 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. 15-RESID-POST-AA
    6. 16255
    Prev
    Next
    INDEX
    Explanations

    a

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    არაუდ
    -0.10
    ordeeld
    -0.10
    ിപ്രായ
    -0.10
    აშაულ
    -0.10
    ისპ
    -0.10
    აჟ
    -0.10
    ძღ
    -0.10
    երձ
    -0.10
    ագահ
    -0.10
    რძნობ
    -0.10
    POSITIVE LOGITS
     mudança
    0.08
    sup
    0.07
     một
    0.07
    thing
    0.07
    there
    0.07
     Certain
    0.07
     установить
    0.07
    chs
    0.07
     At
    0.07
    teva
    0.07
    Activations Density 0.162%

    No Known Activations