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. 54043
    Prev
    Next
    INDEX
    Explanations

    huge

    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
     éclair
    -0.08
     műkö
    -0.08
    观察
    -0.07
     Toss
    -0.07
     kapcsolat
    -0.07
    наз
    -0.07
     SWOT
    -0.07
    nome
    -0.07
    ,以
    -0.07
     touchdown
    -0.07
    POSITIVE LOGITS
     enormous
    0.13
     daunting
    0.13
     tedious
    0.12
     immense
    0.12
     huge
    0.12
     lengthy
    0.12
     umfang
    0.11
     substantial
    0.11
    stantial
    0.11
    �
    0.11
    Activations Density 0.026%

    No Known Activations