© 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. 11-RESID-POST-AA
    6. 108355
    Prev
    Next
    INDEX
    Explanations

    renewal

    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
     الوس
    -0.08
    จัด
    -0.08
     conduite
    -0.07
     mot
    -0.07
    inrin
    -0.07
     Apa
    -0.07
     absor
    -0.07
    ula
    -0.07
     vận
    -0.07
     inventor
    -0.07
    POSITIVE LOGITS
    /re
    0.09
    RE
    0.09
     النه
    0.09
    (RE
    0.09
    _nn
    0.09
     دام
    0.08
     automática
    0.08
    XN
    0.08
     lade
    0.08
    CL
    0.07
    Activations Density 0.005%

    No Known Activations