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. 98426
    Prev
    Next
    INDEX
    Explanations

    Ang

    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
    न्दा
    -0.09
    	comp
    -0.08
    字
    -0.08
    قبل
    -0.07
    нд
    -0.07
     πριν
    -0.07
     τέ
    -0.07
    בחר
    -0.07
    .asm
    -0.07
    مخت
    -0.07
    POSITIVE LOGITS
    strom
    0.12
    riffe
    0.12
    garan
    0.12
    ļu
    0.11
    gota
    0.11
    úst
    0.11
    ्रेज
    0.11
    elernt
    0.10
    kor
    0.10
    uille
    0.10
    Activations Density 0.011%

    No Known Activations