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. 12754
    Prev
    Next
    INDEX
    Explanations

    Liskov Substitution Principle

    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
     Kiwi
    -0.07
    Boom
    -0.07
     prett
    -0.07
     nakak
    -0.07
     Explor
    -0.07
     ورب
    -0.07
     downloader
    -0.07
     convo
    -0.07
     סרט
    -0.07
    archive
    -0.07
    POSITIVE LOGITS
    atil
    0.08
     anxiety
    0.08
    <O
    0.07
    }^{
    0.07
     SLA
    0.07
     anxious
    0.07
    าล
    0.07
     Methode
    0.07
     behar
    0.07
     segons
    0.07
    Activations Density 0.001%

    No Known Activations