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. 12289
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    运输
    -0.08
     CDN
    -0.08
     Comparator
    -0.08
    /sw
    -0.08
    /sh
    -0.08
    Recycler
    -0.07
     recycler
    -0.07
    etam
    -0.07
     ahịa
    -0.07
    CLR
    -0.07
    POSITIVE LOGITS
    ubern
    0.09
    ർന്ന്
    0.09
    ուհ
    0.09
     трев
    0.08
     brunch
    0.08
    _preview
    0.08
    django
    0.08
    ർന്ന
    0.08
     jailed
    0.08
     carreira
    0.08
    Activations Density 0.023%

    No Known Activations