Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53082
    Prev
    Next
    INDEX
    Explanations

    rigorous

    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
     아니다
    -0.09
    .sy
    -0.08
    gro
    -0.08
     Raised
    -0.08
     Kits
    -0.08
     그리고
    -0.08
     obwohl
    -0.08
     dut
    -0.08
     kits
    -0.08
    -dd
    -0.08
    POSITIVE LOGITS
     scrutiny
    0.09
    程度
    0.08
     detail
    0.08
     continental
    0.08
     детал
    0.08
     Adel
    0.07
     paper
    0.07
     scientifique
    0.07
    மான
    0.07
     rig
    0.07
    Activations Density 0.011%

    No Known Activations