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. 12174
    Prev
    Next
    INDEX
    Explanations

    Japanese/Korean

    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
    -0.07
     guida
    -0.07
    нимать
    -0.07
    完善
    -0.07
    Enc
    -0.07
    _attention
    -0.07
    ಮು
    -0.07
     quel
    -0.07
    ಗ್ರ
    -0.07
     filmmaking
    -0.07
    POSITIVE LOGITS
     것은
    0.12
    தால்
    0.12
    ので
    0.11
    തിന്
    0.11
     போது
    0.11
    場合
    0.11
     হলে
    0.10
    时候
    0.10
    തിന
    0.10
     경우
    0.10
    Activations Density 0.019%

    No Known Activations