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. 60981
    Prev
    Next
    INDEX
    Explanations

    prove

    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
     đối
    -0.09
    .dimension
    -0.08
     mémoire
    -0.08
    .coe
    -0.08
     গভ
    -0.08
     അഭിന
    -0.08
     深
    -0.08
     tæ
    -0.08
     traiter
    -0.08
    актор
    -0.08
    POSITIVE LOGITS
     crashes
    0.08
     attempts
    0.08
    Legal
    0.08
    停车
    0.08
     attempted
    0.07
    _File
    0.07
     crash
    0.07
    ่าส
    0.07
    .Unsupported
    0.07
    jay
    0.07
    Activations Density 0.001%

    No Known Activations