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. 106332
    Prev
    Next
    INDEX
    Explanations

    P

    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
     Therap
    -0.10
    >a
    -0.09
     Herstellung
    -0.08
     gg
    -0.08
     postoperative
    -0.08
     anticon
    -0.08
     वितरण
    -0.08
     therapies
    -0.08
     Hardy
    -0.08
     распредел
    -0.08
    POSITIVE LOGITS
     disclosure
    0.08
     submission
    0.08
    acts
    0.08
     auprès
    0.08
     사업
    0.07
     initiatives
    0.07
    応
    0.07
    องค์กร
    0.07
    客户
    0.07
    理念
    0.07
    Activations Density 0.001%

    No Known Activations