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. 19032
    Prev
    Next
    INDEX
    Explanations

    50

    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
     ýü
    -0.10
     gelegenheid
    -0.09
    өкт
    -0.08
    ंबई
    -0.08
     тормош
    -0.08
    irimbo
    -0.08
    aryny
    -0.08
    leton
    -0.08
    地产
    -0.08
    -lein
    -0.08
    POSITIVE LOGITS
    100
    0.10
    0
    0.09
     percent
    0.09
    _percentage
    0.09
    ffffff
    0.09
    ffffffff
    0.08
    percentage
    0.08
    _percent
    0.08
     extremely
    0.08
     sangat
    0.08
    Activations Density 0.006%

    No Known Activations