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. 98126
    Prev
    Next
    INDEX
    Explanations

    Mixed random information

    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
     guud
    -0.08
     quan
    -0.07
     kuni
    -0.07
     inks
    -0.07
     olun
    -0.07
     ink
    -0.07
     hau
    -0.07
    水县
    -0.07
     עד
    -0.07
    enaars
    -0.06
    POSITIVE LOGITS
    iconductor
    0.08
    !,
    0.08
    асыр
    0.07
    hlaba
    0.07
    additional
    0.07
    <data
    0.07
    óvil
    0.07
    Additional
    0.07
    adeed
    0.07
    irango
    0.07
    Activations Density 0.118%

    No Known Activations