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. 45683
    Prev
    Next
    INDEX
    Explanations

    root

    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
     کرا
    -0.08
     వరకు
    -0.08
    まで
    -0.08
     قدرت
    -0.08
     نوي
    -0.08
     ekstrem
    -0.07
    [tag
    -0.07
     crazy
    -0.07
     unik
    -0.07
     ಪರ
    -0.07
    POSITIVE LOGITS
     evidenced
    0.07
     unnoticed
    0.07
     boul
    0.07
     george
    0.07
     lurking
    0.07
     parmi
    0.07
    Condition
    0.07
    qin
    0.07
     disguised
    0.07
    bru
    0.07
    Activations Density 0.020%

    No Known Activations