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. 11929
    Prev
    Next
    INDEX
    Explanations

    Providing Instructions/Context

    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
     motorcycles
    -0.09
    全国
    -0.08
    物
    -0.08
    出售
    -0.08
     motoc
    -0.08
     BMX
    -0.08
     valg
    -0.08
     метро
    -0.08
     vendu
    -0.08
     biologique
    -0.08
    POSITIVE LOGITS
     स्पष्ट
    0.11
     Specify
    0.11
     Explicit
    0.10
     уточ
    0.10
    Specify
    0.10
     explicitly
    0.10
     specifying
    0.10
     Assistant
    0.10
     specify
    0.09
     explíc
    0.09
    Activations Density 0.014%

    No Known Activations