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. 60700
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     slippery
    -0.10
     pavement
    -0.08
    以下
    -0.08
    Bandwidth
    -0.08
     nicotine
    -0.08
    Consent
    -0.08
     loaf
    -0.08
     கூட
    -0.08
    _vlan
    -0.08
    "As
    -0.08
    POSITIVE LOGITS
    öz
    0.08
     举报
    0.08
     vector
    0.08
    bewertungen
    0.08
     QVector
    0.08
     ради
    0.07
    alte
    0.07
    neal
    0.07
     sqrt
    0.07
     ive
    0.07
    Activations Density 0.019%

    No Known Activations