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. 56048
    Prev
    Next
    INDEX
    Explanations

    Russian

    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
     пригод
    -0.08
     fo
    -0.08
     Fo
    -0.08
     ਕੰ
    -0.07
     Sf
    -0.07
     SF
    -0.07
     spec
    -0.07
    785
    -0.07
     abort
    -0.07
    sf
    -0.07
    POSITIVE LOGITS
     Precious
    0.09
     herv
    0.08
    קת
    0.08
    辨
    0.08
    액
    0.08
     promin
    0.08
     niches
    0.08
     jean
    0.08
     kaz
    0.08
     выдел
    0.08
    Activations Density 0.006%

    No Known Activations