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. 11-RESID-POST-AA
    6. 12925
    Prev
    Next
    INDEX
    Explanations

    Meet and greet opportunities

    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
     discolor
    -0.08
    Encoded
    -0.08
    编码
    -0.08
    訂
    -0.08
    Encode
    -0.08
    আমি
    -0.08
    encoded
    -0.07
    Encoding
    -0.07
    .encode
    -0.07
     decking
    -0.07
    POSITIVE LOGITS
     personable
    0.10
    互动
    0.10
     Nähe
    0.10
     celebrities
    0.09
     бли
    0.09
     approachable
    0.09
     Begegn
    0.09
     backstage
    0.09
     intimacy
    0.09
     celebrity
    0.08
    Activations Density 0.053%

    No Known Activations