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. 77196
    Prev
    Next
    INDEX
    Explanations

    photosynthesis

    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
     duch
    -0.09
     ший
    -0.08
    ються
    -0.08
    .php
    -0.08
     జిల్లా
    -0.08
    юцца
    -0.07
     Martínez
    -0.07
     జిల్ల
    -0.07
    钻
    -0.07
    േഷ്
    -0.07
    POSITIVE LOGITS
     mankind
    0.09
     पृथ
    0.09
     humans
    0.09
     fungi
    0.09
     공급
    0.08
     extracts
    0.08
     potable
    0.08
     oxygen
    0.08
     الطبيعية
    0.08
    _Open
    0.08
    Activations Density 0.004%

    No Known Activations