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. 43080
    Prev
    Next
    INDEX
    Explanations

    necessary

    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
     folgend
    -0.08
    贫
    -0.08
     dieting
    -0.08
     poverty
    -0.08
     jóvenes
    -0.08
     olay
    -0.08
     подрост
    -0.08
     నివ
    -0.08
    这样的
    -0.08
     এখনও
    -0.07
    POSITIVE LOGITS
    तान
    0.09
     необходим
    0.09
     precautions
    0.09
     infrastructure
    0.09
     erforder
    0.08
    itated
    0.08
     compétences
    0.08
    措施
    0.08
    事項
    0.08
     szüks
    0.08
    Activations Density 0.015%

    No Known Activations