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. 77374
    Prev
    Next
    INDEX
    Explanations

    stories/conversations

    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
     تحمل
    -0.08
    iksaan
    -0.08
    ogs
    -0.07
    	debug
    -0.07
     dig
    -0.07
     выполнение
    -0.07
    取
    -0.07
    	params
    -0.07
    _trace
    -0.07
    ther
    -0.07
    POSITIVE LOGITS
    third
    0.10
     third
    0.09
     മൂന്ന
    0.09
     fourth
    0.09
     तीस
    0.09
     معهم
    0.09
     terceira
    0.08
    .third
    0.08
     terceiro
    0.08
     ثالث
    0.08
    Activations Density 0.255%

    No Known Activations