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. 23-RESID-POST-AA
    6. 130729
    Prev
    Next
    INDEX
    Explanations

    mathematical forumlas

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inteira
    -0.08
    -0.08
     >>↵↵
    -0.07
    ushima
    -0.07
     continente
    -0.07
     Are
    -0.07
    entar
    -0.07
     unfolds
    -0.07
    said
    -0.07
     separation
    -0.07
    POSITIVE LOGITS
     collegiate
    0.09
     NCAA
    0.08
    _subject
    0.08
    viles
    0.08
    -war
    0.07
     accessor
    0.07
    Subjects
    0.07
    _mesh
    0.07
     kişiler
    0.07
    _questions
    0.07
    Activations Density 0.001%

    No Known Activations