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. 23-RESID-POST-AA
    6. 98534
    Prev
    Next
    INDEX
    Explanations

    satin, matte finishes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trakt
    -0.08
     xmm
    -0.08
     whitespace
    -0.08
     Fn
    -0.07
    _det
    -0.07
    Yn
    -0.07
     таны
    -0.07
    	end
    -0.07
     Judaism
    -0.07
    ষ্ট
    -0.07
    POSITIVE LOGITS
     satin
    0.16
     мат
    0.11
     сат
    0.11
     pear
    0.11
     sat
    0.11
     subdued
    0.11
     mat
    0.11
     مات
    0.11
     pearl
    0.10
     matt
    0.10
    Activations Density 0.022%

    No Known Activations