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. 77455
    Prev
    Next
    INDEX
    Explanations

    Business cards

    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
     gyn
    -0.10
    lim
    -0.08
     estrogen
    -0.08
     muscles
    -0.08
    Truthy
    -0.08
    ryn
    -0.08
     vmax
    -0.07
    Ис
    -0.07
     operasi
    -0.07
    ск
    -0.07
    POSITIVE LOGITS
    紙
    0.10
     карточ
    0.09
    纸
    0.09
     футбол
    0.09
     papel
    0.09
     الشخصية
    0.09
     boosters
    0.09
     البلا
    0.09
    უბლ
    0.09
    पत्र
    0.09
    Activations Density 0.039%

    No Known Activations