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. 111775
    Prev
    Next
    INDEX
    Explanations

    Date or Type

    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
    Think
    -0.08
    ত্য
    -0.08
    Thinking
    -0.07
    _mv
    -0.07
    .Parameters
    -0.07
    vek
    -0.07
    %c
    -0.07
     Vorr
    -0.07
    'avez
    -0.07
    oa
    -0.07
    POSITIVE LOGITS
    별
    0.09
     Albert
    0.08
     desc
    0.07
     matters
    0.07
     dubb
    0.07
    Produced
    0.07
     asc
    0.07
     gu
    0.07
     hinweg
    0.07
     flown
    0.07
    Activations Density 0.054%

    No Known Activations