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. 15-RESID-POST-AA
    6. 19198
    Prev
    Next
    INDEX
    Explanations

    legal agreements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pig
    -0.08
    Any
    -0.08
    _FLAG
    -0.08
    .bc
    -0.08
    _probability
    -0.08
    _symbol
    -0.08
    @Path
    -0.08
    _MASK
    -0.08
    _Input
    -0.08
     newcom
    -0.08
    POSITIVE LOGITS
     unaffected
    0.09
    !!!!
    0.09
     vigueur
    0.09
     полноцен
    0.09
    !!↵↵
    0.08
     күш
    0.08
     прекрасно
    0.08
     governing
    0.08
     قوية
    0.08
     great
    0.08
    Activations Density 0.001%

    No Known Activations