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. 12780
    Prev
    Next
    INDEX
    Explanations

    trapezoids and midpoints

    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
     tabindex
    -0.09
    .er
    -0.08
     colocar
    -0.08
     enthr
    -0.08
     émissions
    -0.08
     prochain
    -0.08
    ล่าสุด
    -0.08
     знач
    -0.07
    zut
    -0.07
     excellence
    -0.07
    POSITIVE LOGITS
     Equivalent
    0.09
    0.08
    Equivalent
    0.08
    oppel
    0.08
     equival
    0.08
     equivalent
    0.08
     نصف
    0.08
     étude
    0.08
     Studie
    0.07
     studi
    0.07
    Activations Density 0.044%

    No Known Activations