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. 58597
    Prev
    Next
    INDEX
    Explanations

    russian reflexive suffixes

    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
     tulee
    -0.08
     Wagner
    -0.08
    �
    -0.08
     anniversaire
    -0.08
    Responses
    -0.08
    -devel
    -0.07
    Standalone
    -0.07
    aceous
    -0.07
    stit
    -0.07
     Stored
    -0.07
    POSITIVE LOGITS
     accessing
    0.09
     hart
    0.07
     utilize
    0.07
     Muz
    0.07
     synd
    0.07
     pun
    0.07
     тому
    0.07
     gah
    0.07
    Dallas
    0.07
     unaffected
    0.07
    Activations Density 0.021%

    No Known Activations