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. 102798
    Prev
    Next
    INDEX
    Explanations

    quantum computing

    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
     کسب
    -0.10
     Happiness
    -0.08
     Bengals
    -0.08
     मुंबई
    -0.08
     Kinect
    -0.08
     Torch
    -0.08
     adicionales
    -0.08
     дополнитель
    -0.08
     Volleyball
    -0.08
    점
    -0.08
    POSITIVE LOGITS
     crypto
    0.10
    Crypt
    0.10
     крип
    0.09
     looming
    0.09
    -resistant
    0.09
    -proof
    0.09
     thwart
    0.09
    Post
    0.09
    Modern
    0.09
    Until
    0.09
    Activations Density 0.004%

    No Known Activations