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. 61042
    Prev
    Next
    INDEX
    Explanations

    beautiful

    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
    213
    -0.08
     скла
    -0.08
     Bere
    -0.08
    .Strict
    -0.08
     Bez
    -0.08
     letz
    -0.08
    stat
    -0.08
     Elimin
    -0.07
     contrário
    -0.07
    .COM
    -0.07
    POSITIVE LOGITS
    丽
    0.11
     đẹp
    0.11
    麗
    0.10
     mắt
    0.10
     vapor
    0.09
     thật
    0.09
     सुंदर
    0.09
     bath
    0.08
    しい
    0.08
     kakhulu
    0.08
    Activations Density 0.037%

    No Known Activations