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. 43791
    Prev
    Next
    INDEX
    Explanations

    luggage

    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
     SR
    -0.08
     svega
    -0.08
     agriculture
    -0.07
     Knox
    -0.07
     illusion
    -0.07
     stripe
    -0.07
    سسات
    -0.07
    ناد
    -0.07
     rara
    -0.07
     brz
    -0.07
    POSITIVE LOGITS
    স্থ
    0.09
    Ray
    0.08
     warmth
    0.08
     compartments
    0.08
    restr
    0.08
    _management
    0.07
    箱
    0.07
    Dive
    0.07
    -port
    0.07
     الطرف
    0.07
    Activations Density 0.006%

    No Known Activations