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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 53291
    Prev
    Next
    INDEX
    Explanations

    lottery numbers

    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
    _fname
    -0.07
    _OK
    -0.07
     northwest
    -0.07
     lexi
    -0.07
     '/../
    -0.07
     Zhu
    -0.07
     diminution
    -0.07
    aham
    -0.07
     abstr
    -0.07
     Gabri
    -0.07
    POSITIVE LOGITS
     bonus
    0.08
    Public
    0.08
     જાહેર
    0.08
     ആയി
    0.08
    Bonus
    0.08
     explosive
    0.08
    bonus
    0.08
     olimp
    0.07
    public
    0.07
     olímp
    0.07
    Activations Density 0.008%

    No Known Activations