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. 19077
    Prev
    Next
    INDEX
    Explanations

    curling

    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
     pandémie
    -0.09
     pandemia
    -0.08
    .attrs
    -0.08
     toxicity
    -0.08
     Pandemie
    -0.07
     storia
    -0.07
     complexities
    -0.07
     пандем
    -0.07
     nomen
    -0.07
    нознач
    -0.07
    POSITIVE LOGITS
     alrededor
    0.11
     around
    0.10
     вокруг
    0.10
     surrounding
    0.10
     nearby
    0.09
     आसपास
    0.09
     Around
    0.09
     जव
    0.09
    around
    0.09
    Around
    0.09
    Activations Density 0.002%

    No Known Activations