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. 78634
    Prev
    Next
    INDEX
    Explanations

    #:

    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
     meetings
    -0.08
     Beton
    -0.07
     roads
    -0.07
     Eltern
    -0.07
     interrog
    -0.07
    .Flat
    -0.07
     sche
    -0.07
     an
    -0.07
     entrepreneurs
    -0.07
     historians
    -0.07
    POSITIVE LOGITS
     DARK
    0.09
     bf
    0.08
    번호
    0.08
     विष
    0.08
     Museu
    0.08
    kil
    0.08
     الرابط
    0.08
     Selling
    0.08
    ixels
    0.08
    kung
    0.07
    Activations Density 0.017%

    No Known Activations