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. 45083
    Prev
    Next
    INDEX
    Explanations

    without

    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
     znajduje
    -0.09
    ्ज
    -0.09
     ausz
    -0.08
    577
    -0.08
    ieb
    -0.08
    osi
    -0.08
    ellte
    -0.08
    	cp
    -0.07
     gesproken
    -0.07
    ichten
    -0.07
    POSITIVE LOGITS
    才能
    0.09
     maka
    0.09
     않는
    0.09
     adanya
    0.09
     fundamentally
    0.08
     الرك
    0.08
     mekan
    0.08
     તો
    0.08
     ποτέ
    0.08
    ாமல்
    0.08
    Activations Density 0.040%

    No Known Activations