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. 120377
    Prev
    Next
    INDEX
    Explanations

    and

    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
    buch
    -0.09
    Genesis
    -0.08
    서
    -0.08
     가능합니다
    -0.08
     Genesis
    -0.08
     euth
    -0.08
    acting
    -0.08
    ক্রম
    -0.08
    кор
    -0.08
     더욱
    -0.08
    POSITIVE LOGITS
     workings
    0.08
     कि
    0.07
    _min
    0.07
    app
    0.07
     место
    0.07
     Haw
    0.07
     mà
    0.07
     ;
    0.07
    appa
    0.07
     min
    0.07
    Activations Density 0.049%

    No Known Activations