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. 15-RESID-POST-AA
    6. 184
    Prev
    Next
    INDEX
    Explanations

    experience

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feest
    -0.08
     определяется
    -0.08
    nete
    -0.08
    pecies
    -0.07
     housekeeping
    -0.07
     SNP
    -0.07
     jogadores
    -0.07
    ête
    -0.07
     мел
    -0.07
     игроков
    -0.07
    POSITIVE LOGITS
     firsthand
    0.19
     witnessing
    0.14
     experiences
    0.14
    経験
    0.14
     experience
    0.13
    体验
    0.13
     경험
    0.13
    experience
    0.12
     experiencing
    0.12
     experiencias
    0.12
    Activations Density 0.160%

    No Known Activations