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. 43821
    Prev
    Next
    INDEX
    Explanations

    icebergs and pyramids

    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
     স্থান
    -0.08
     bishop
    -0.07
     지정
    -0.07
     masz
    -0.07
     ना
    -0.07
    ировку
    -0.07
    েজ
    -0.07
     hallmark
    -0.07
     ইং
    -0.07
     장소
    -0.07
    POSITIVE LOGITS
     herum
    0.10
    沃
    0.09
     depicted
    0.09
     pathogenic
    0.08
     Plot
    0.08
     profond
    0.08
     encomp
    0.08
     Drawable
    0.08
     plotted
    0.08
     concent
    0.08
    Activations Density 0.022%

    No Known Activations