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. 106218
    Prev
    Next
    INDEX
    Explanations

    new

    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
    background
    -0.09
    wale
    -0.08
    registered
    -0.08
    ylan
    -0.08
    panel
    -0.08
     నేప
    -0.07
    eight
    -0.07
     panneaux
    -0.07
     shortlisted
    -0.07
    air
    -0.07
    POSITIVE LOGITS
    玩法
    0.10
    Idx
    0.09
     طرق
    0.08
    新时代
    0.08
     taxonomy
    0.08
    шие
    0.08
     चिकित्स
    0.08
    	idx
    0.08
     beg
    0.08
     طب
    0.08
    Activations Density 0.039%

    No Known Activations