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. 78293
    Prev
    Next
    INDEX
    Explanations

    Mali

    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
    Plac
    -0.08
     endothelial
    -0.08
     trast
    -0.08
    /delete
    -0.08
     laser
    -0.07
    (children
    -0.07
     premium
    -0.07
    osome
    -0.07
     Schr
    -0.07
    .xaml
    -0.07
    POSITIVE LOGITS
     Senegal
    0.11
     Debian
    0.09
     Mali
    0.09
     Kant
    0.08
     caste
    0.08
     Burkina
    0.08
    Tensor
    0.08
     apprenticeship
    0.08
     Sénégal
    0.08
    围
    0.08
    Activations Density 0.007%

    No Known Activations