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. 98154
    Prev
    Next
    INDEX
    Explanations

    rate

    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
    route
    -0.10
    ENTES
    -0.08
    esor
    -0.08
    anned
    -0.08
    eltas
    -0.08
    ENTE
    -0.08
    rights
    -0.08
    routes
    -0.08
     relaties
    -0.08
    ಿಂದ
    -0.08
    POSITIVE LOGITS
    payer
    0.13
    असल
    0.11
    Limiter
    0.11
     (%)
    0.10
    是多少
    0.10
     limiting
    0.10
    -rata
    0.10
    -of
    0.09
    _constant
    0.09
     limiter
    0.09
    Activations Density 0.039%

    No Known Activations