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. 112225
    Prev
    Next
    INDEX
    Explanations

    limited

    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
     rapporto
    -0.07
     निर्देशन
    -0.07
    	ex
    -0.07
    र्शन
    -0.07
     indeed
    -0.07
    ensen
    -0.07
    ਵਾ
    -0.07
     havoc
    -0.07
     индивиду
    -0.07
     jangan
    -0.07
    POSITIVE LOGITS
    情侣
    0.08
    arily
    0.08
     waarop
    0.08
     tokko
    0.08
     munhu
    0.08
     দ
    0.08
     çift
    0.08
    (?)
    0.07
     unanimously
    0.07
     waarbij
    0.07
    Activations Density 0.072%

    No Known Activations