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. 29795
    Prev
    Next
    INDEX
    Explanations

    non-breaking spaces

    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
     medit
    -0.10
     yu
    -0.09
     meditate
    -0.08
     '';↵↵
    -0.08
     ciek
    -0.08
     dzie
    -0.07
     ATH
    -0.07
     mwa
    -0.07
     '';↵
    -0.07
    '];?></
    -0.07
    POSITIVE LOGITS
     preventing
    0.09
    (IService
    0.08
    ुओं
    0.08
    .I
    0.08
     Iyo
    0.08
    .arguments
    0.07
    efe
    0.07
     IService
    0.07
    .parameters
    0.07
     prévention
    0.07
    Activations Density 0.000%

    No Known Activations