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. 112100
    Prev
    Next
    INDEX
    Explanations

    offering

    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
     Cin
    -0.08
     Bars
    -0.07
    (fig
    -0.07
    ornos
    -0.07
     Fritz
    -0.07
    orno
    -0.07
    /Linux
    -0.07
     regula
    -0.07
     قراءة
    -0.07
    @y
    -0.07
    POSITIVE LOGITS
     ډول
    0.09
     الدراسي
    0.09
     종류
    0.09
    별
    0.09
    types
    0.08
     다양
    0.08
     tailored
    0.08
    ประเภท
    0.08
     desple
    0.08
     diversification
    0.08
    Activations Density 0.158%

    No Known Activations