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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98322
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    能够
    -0.14
    能
    -0.11
     kunna
    -0.11
     能
    -0.10
     بتوان
    -0.09
    <|return|>
    -0.09
     ના
    -0.09
     可以
    -0.08
     realities
    -0.08
    ness
    -0.08
    POSITIVE LOGITS
    ’t
    0.24
    ´t
    0.19
     certainement
    0.17
     easily
    0.17
     fácilmente
    0.17
     facilmente
    0.17
    ‘t
    0.16
     facilement
    0.16
     بسهولة
    0.16
     safely
    0.16
    Activations Density 0.122%

    No Known Activations