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. 44620
    Prev
    Next
    INDEX
    Explanations

    for

    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
    =("
    -0.09
     Nad
    -0.07
    centage
    -0.07
    .Dock
    -0.07
     Çok
    -0.07
    _Global
    -0.07
     Händen
    -0.07
     Mt
    -0.07
     effetti
    -0.07
    .Enum
    -0.07
    POSITIVE LOGITS
     why
    0.10
     warum
    0.09
     überhaupt
    0.09
    为何
    0.08
     بالس
    0.08
     bother
    0.08
    如此
    0.08
     waarom
    0.08
    为什么
    0.08
     возникновения
    0.08
    Activations Density 0.097%

    No Known Activations