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

    Neuronpedia

    APICircuit 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. 43956
    Prev
    Next
    INDEX
    Explanations

    flush

    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
    нику
    -0.08
    никам
    -0.08
     pla
    -0.08
     bask
    -0.08
    ித்து
    -0.08
     godzin
    -0.08
     மற
    -0.07
     정
    -0.07
     reve
    -0.07
     ass
    -0.07
    POSITIVE LOGITS
     light
    0.08
    保障
    0.07
    itage
    0.07
    也
    0.07
     ransomware
    0.07
    خصص
    0.07
     discrimination
    0.07
     safeguarding
    0.07
    -light
    0.07
     műkö
    0.07
    Activations Density 0.001%

    No Known Activations