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. 11680
    Prev
    Next
    INDEX
    Explanations

    new

    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
     LAD
    -0.08
     Cet
    -0.08
     Qa
    -0.08
     тө
    -0.07
     Teg
    -0.07
     Vi
    -0.07
     gloves
    -0.07
     Juríd
    -0.07
    .COMP
    -0.07
     VID
    -0.07
    POSITIVE LOGITS
    spaper
    0.08
    necessarily
    0.08
    Employee
    0.08
    bie
    0.08
    Opt
    0.07
    bidden
    0.07
    (二
    0.07
    virtual
    0.07
    isible
    0.07
    ๆ
    0.07
    Activations Density 0.003%

    No Known Activations