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. 113021
    Prev
    Next
    INDEX
    Explanations

    **

    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
    om
    -0.07
    मता
    -0.07
            	↵
    -0.07
    �
    -0.07
     veneer
    -0.07
    Provided
    -0.06
    Trailing
    -0.06
    指标
    -0.06
     footh
    -0.06
    ਮੀ
    -0.06
    POSITIVE LOGITS
     funcionarios
    0.09
     EMPTY
    0.09
     Sophia
    0.09
    EMPTY
    0.09
     রয়েছে
    0.08
     روس
    0.08
     adet
    0.08
     russ
    0.08
     Luk
    0.07
     представляет
    0.07
    Activations Density 0.017%

    No Known Activations