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. 11737
    Prev
    Next
    INDEX
    Explanations

    on

    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
    keits
    -0.09
     varios
    -0.09
    าคาร
    -0.09
     Really
    -0.08
    achement
    -0.08
    ถาน
    -0.08
     عدة
    -0.08
    หลาย
    -0.08
     بالكامل
    -0.08
     several
    -0.08
    POSITIVE LOGITS
    ☺
    0.08
    Protocols
    0.08
     Rosa
    0.07
    _imgs
    0.07
    	sleep
    0.07
     aprim
    0.07
     pach
    0.07
     yacht
    0.07
     sleep
    0.07
     autobi
    0.07
    Activations Density 0.000%

    No Known Activations