Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 43231
    Prev
    Next
    INDEX
    Explanations

    mathematical notation/logic

    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
     εφαρμο
    -0.08
    ighe
    -0.08
     nabij
    -0.08
     afhankelijk
    -0.08
     Reifen
    -0.07
    hee
    -0.07
    .child
    -0.07
    ?>↵↵↵
    -0.07
     Nis
    -0.07
    _child
    -0.07
    POSITIVE LOGITS
     restantes
    0.10
     disbelief
    0.09
     blacklist
    0.08
     distrust
    0.08
     excludes
    0.08
     exclusion
    0.08
    0.08
     ennem
    0.08
     exclusions
    0.08
     restante
    0.08
    Activations Density 0.084%

    No Known Activations