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. 76939
    Prev
    Next
    INDEX
    Explanations

    Foucault

    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
     cubic
    -0.09
     donor
    -0.08
     Toon
    -0.08
    超过
    -0.08
     modulus
    -0.08
     Bewertung
    -0.07
    平方
    -0.07
    电影
    -0.07
    影视
    -0.07
     Gst
    -0.07
    POSITIVE LOGITS
    iptables
    0.10
     perme
    0.08
     सत्ता
    0.08
    journal
    0.08
    ..."↵
    0.08
    Contin
    0.08
    Knowledge
    0.08
    0.08
    ..."↵↵
    0.08
    Firewall
    0.08
    Activations Density 0.002%

    No Known Activations