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. 12864
    Prev
    Next
    INDEX
    Explanations

    ite

    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
     Pey
    -0.10
    	dto
    -0.08
     poniendo
    -0.08
    spolit
    -0.08
    	ent
    -0.08
    	Method
    -0.08
    ayeen
    -0.08
    	Version
    -0.08
    .backward
    -0.08
    icent
    -0.08
    POSITIVE LOGITS
     countertops
    0.10
    纹
    0.09
     biom
    0.08
     fels
    0.08
     Astro
    0.08
     Biom
    0.08
     biomarkers
    0.08
     snowboard
    0.08
     컬
    0.08
     waters
    0.07
    Activations Density 0.006%

    No Known Activations