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. 98239
    Prev
    Next
    INDEX
    Explanations

    te

    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
    지난
    -0.08
    ihuahua
    -0.08
     지난
    -0.08
    ELLOW
    -0.08
     해당
    -0.08
     soz
    -0.08
     Tayy
    -0.07
    �
    -0.07
     Sö
    -0.07
    ovanju
    -0.07
    POSITIVE LOGITS
    cnica
    0.14
    aching
    0.12
    cnico
    0.12
    atro
    0.12
    eth
    0.12
    λευτα
    0.11
    klif
    0.11
    cn
    0.11
    ens
    0.11
    krar
    0.10
    Activations Density 0.003%

    No Known Activations