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. 54072
    Prev
    Next
    INDEX
    Explanations

    formulas

    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
    .`
    -0.08
    *(
    -0.08
     fract
    -0.08
    |-
    -0.07
    (fl
    -0.07
     Packet
    -0.07
    .)↵↵
    -0.07
     Canal
    -0.07
     Jalan
    -0.07
    .NET
    -0.07
    POSITIVE LOGITS
    Downloads
    0.08
    ould
    0.08
    _hide
    0.08
    uawei
    0.08
     будут
    0.08
     숨
    0.08
    Arial
    0.07
     ترب
    0.07
     დიდ
    0.07
     recomenda
    0.07
    Activations Density 0.002%

    No Known Activations