Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 102794
    Prev
    Next
    INDEX
    Explanations

    vm

    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
     عز
    -0.08
     хозя
    -0.08
     Пот
    -0.07
     За
    -0.07
     ป
    -0.07
     คาสิโน
    -0.07
     Development
    -0.07
     Hospital
    -0.07
    Development
    -0.07
     الأحمر
    -0.07
    POSITIVE LOGITS
    ៍
    0.09
    ின்
    0.09
    ்களின்
    0.08
    ుతో
    0.08
    race
    0.08
    ��
    0.08
    ுடன்
    0.08
    の
    0.07
     mich
    0.07
    €™
    0.07
    Activations Density 0.088%

    No Known Activations