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. 112966
    Prev
    Next
    INDEX
    Explanations

    binary multiplication

    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
     З
    -0.08
     Possible
    -0.08
     dbo
    -0.07
     בפני
    -0.07
     perante
    -0.07
    ABL
    -0.07
    ZO
    -0.07
     Z
    -0.07
     टिप
    -0.07
     □
    -0.07
    POSITIVE LOGITS
    aneo
    0.08
    chains
    0.08
    tection
    0.07
    clusters
    0.07
    pods
    0.07
    .rate
    0.07
     synd
    0.07
    onth
    0.07
    pendent
    0.07
    rate
    0.07
    Activations Density 0.004%

    No Known Activations