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. 98184
    Prev
    Next
    INDEX
    Explanations

    dém/Ay

    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
     Luther
    -0.09
     oraz
    -0.08
    itso
    -0.07
    দ্ধ
    -0.07
    াঠ
    -0.07
    prest
    -0.07
     Woodstock
    -0.07
     ba
    -0.07
     girl
    -0.07
     lupus
    -0.07
    POSITIVE LOGITS
    ico
    0.08
    Комп
    0.07
    Identifier
    0.07
    	post
    0.07
     funzione
    0.07
    Mask
    0.07
     comen
    0.07
    	event
    0.07
     كور
    0.07
     얼굴
    0.07
    Activations Density 0.001%

    No Known Activations