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. 11-RESID-POST-AA
    6. 58456
    Prev
    Next
    INDEX
    Explanations

    disk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roz
    -0.08
    inqu
    -0.08
    															
    -0.07
     REFER
    -0.07
    _INTERVAL
    -0.07
     Title
    -0.07
     pola
    -0.07
     DATA
    -0.07
    ◇
    -0.07
    ,str
    -0.07
    POSITIVE LOGITS
    дун
    0.08
    lua
    0.08
    beras
    0.08
    .je
    0.08
    .blit
    0.07
    _lengths
    0.07
    [:]
    0.07
    werkt
    0.07
    helm
    0.07
    အသ
    0.07
    Activations Density 0.001%

    No Known Activations