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. 112867
    Prev
    Next
    INDEX
    Explanations

    Russian

    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
     breakthroughs
    -0.08
     breakthrough
    -0.08
    baseline
    -0.07
    そこで
    -0.07
    ján
    -0.07
     mentions
    -0.07
    interrupt
    -0.07
    تمر
    -0.07
    sz
    -0.07
    ার্স
    -0.07
    POSITIVE LOGITS
     Farben
    0.09
     nne
    0.08
     Accessibility
    0.08
     Serializer
    0.08
     ад
    0.08
     Nina
    0.08
     Transparency
    0.08
     любые
    0.08
     kaikki
    0.08
     Nin
    0.08
    Activations Density 0.011%

    No Known Activations