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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 77022
    Prev
    Next
    INDEX
    Explanations

    make

    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
    院
    -0.08
     Ribbon
    -0.08
     impair
    -0.08
    ]↵↵
    -0.07
    一点
    -0.07
     vl
    -0.07
     UNC
    -0.07
     Ary
    -0.07
    خفض
    -0.07
     التع
    -0.07
    POSITIVE LOGITS
    (mesh
    0.09
     sludge
    0.08
    Guid
    0.08
    (headers
    0.08
    (fr
    0.08
    rices
    0.08
     guider
    0.08
    frames
    0.08
    .guid
    0.07
     guid
    0.07
    Activations Density 0.001%

    No Known Activations