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. 52990
    Prev
    Next
    INDEX
    Explanations

    Russian research terms

    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
    FIL
    -0.10
    مل
    -0.09
    Uit
    -0.09
     forcing
    -0.08
     Trick
    -0.08
     مل
    -0.08
    ವೇ
    -0.08
     Spiegel
    -0.08
    فات
    -0.07
    ìn
    -0.07
    POSITIVE LOGITS
    航
    0.09
     menée
    0.08
     Bren
    0.08
     undertaken
    0.08
    ોને
    0.07
     നടത്തുന്ന
    0.07
     труд
    0.07
    teams
    0.07
     Kam
    0.07
     �
    0.07
    Activations Density 0.004%

    No Known Activations