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. 49387
    Prev
    Next
    INDEX
    Explanations

    dis

    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
    út
    -0.08
     Rendez
    -0.08
    .fixed
    -0.07
    Pu
    -0.07
    ಾಡ
    -0.07
     Pu
    -0.07
     suspected
    -0.07
    cup
    -0.07
    ಾಗ
    -0.07
     alf
    -0.07
    POSITIVE LOGITS
     ਗ
    0.07
    _warning
    0.07
     höf
    0.07
     Scarlett
    0.07
    _cc
    0.07
    .Restr
    0.07
     เล
    0.07
    不能
    0.07
     Cannot
    0.07
    _echo
    0.07
    Activations Density 0.021%

    No Known Activations