Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 54025
    Prev
    Next
    INDEX
    Explanations

    skirt

    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
     தொடர்ப
    -0.09
    assy
    -0.08
    Golden
    -0.08
    nergie
    -0.08
     Jahren
    -0.08
     সম্পর্ক
    -0.08
     Golden
    -0.07
     قوية
    -0.07
     encouraging
    -0.07
    {sub
    -0.07
    POSITIVE LOGITS
     вместо
    0.08
     CDI
    0.08
     whereas
    0.08
     calves
    0.08
     ahubwo
    0.07
     Babies
    0.07
    	delete
    0.07
     хотя
    0.07
    например
    0.07
     kodwa
    0.07
    Activations Density 0.026%

    No Known Activations