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. 60572
    Prev
    Next
    INDEX
    Explanations

    所有

    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
     drunken
    -0.08
    Suitable
    -0.08
    ıdır
    -0.08
     ocorre
    -0.08
    Occurs
    -0.08
     εμφαν
    -0.08
    _mt
    -0.08
     sollen
    -0.07
    Appearance
    -0.07
    POSITIVE LOGITS
    ありがとうございました
    0.13
    感谢
    0.12
    ,谢谢
    0.11
     thank
    0.11
     Thank
    0.11
     THANK
    0.11
     thanking
    0.11
     sayesinde
    0.10
     Vielen
    0.10
    thank
    0.10
    Activations Density 0.094%

    No Known Activations