Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19364
    Prev
    Next
    INDEX
    Explanations

    say water or moisture

    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
    ictions
    -0.08
     heu
    -0.08
     connector
    -0.08
    (-
    -0.08
     experiments
    -0.07
    _connection
    -0.07
     célib
    -0.07
     partik
    -0.07
    icted
    -0.07
    выя
    -0.07
    POSITIVE LOGITS
     Middleware
    0.08
     shimmering
    0.08
    ANTED
    0.07
     दस्त
    0.07
     朝
    0.07
    .Spec
    0.07
    Permit
    0.07
    Readable
    0.07
     页面
    0.07
    adda
    0.07
    Activations Density 0.001%

    No Known Activations