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. 78742
    Prev
    Next
    INDEX
    Explanations

    overall

    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
     allein
    -0.08
    행
    -0.08
     فرصت
    -0.08
     Alone
    -0.08
     kait
    -0.08
     sudden
    -0.07
    ыза
    -0.07
     alone
    -0.07
    .RO
    -0.07
    .file
    -0.07
    POSITIVE LOGITS
    vart
    0.08
    综合
    0.08
     Tent
    0.08
     Theta
    0.08
    uffix
    0.08
    icloud
    0.07
     Steen
    0.07
    şik
    0.07
     Bum
    0.07
    plaat
    0.07
    Activations Density 0.009%

    No Known Activations