© 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. 13147
    Prev
    Next
    INDEX
    Explanations

    but

    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
    轴
    -0.08
     umbes
    -0.07
     incarcerated
    -0.07
     regiment
    -0.07
     melakukan
    -0.07
    Firm
    -0.07
     ELE
    -0.07
     lain
    -0.07
    rawdę
    -0.07
    (axis
    -0.07
    POSITIVE LOGITS
    کی
    0.08
    brite
    0.07
     Nan
    0.07
     Barg
    0.07
    _loop
    0.07
     کړئ
    0.07
     pere
    0.07
    景
    0.07
    gas
    0.07
    �
    0.07
    Activations Density 0.039%

    No Known Activations