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. 106199
    Prev
    Next
    INDEX
    Explanations

    report

    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
     Mehrheit
    -0.08
    Polyline
    -0.08
     Aufnahme
    -0.08
    -0.08
    Icon
    -0.08
    asten
    -0.08
     Blur
    -0.07
     probi
    -0.07
     Icon
    -0.07
    ENTRY
    -0.07
    POSITIVE LOGITS
     thống
    0.08
    _requested
    0.08
    (di
    0.08
    Requested
    0.08
     rapports
    0.08
    .Generate
    0.08
     requested
    0.08
    .subplots
    0.08
     generating
    0.08
     düzen
    0.08
    Activations Density 0.012%

    No Known Activations