Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113071
    Prev
    Next
    INDEX
    Explanations

    |

    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
    orithm
    -0.08
     расч
    -0.08
    accepted
    -0.08
    _if
    -0.07
     accepted
    -0.07
     गण
    -0.07
    riage
    -0.07
    렬
    -0.07
     proporcionar
    -0.07
     ગણ
    -0.07
    POSITIVE LOGITS
     SZ
    0.08
     Fidel
    0.08
    чера
    0.07
    /theme
    0.07
    .cs
    0.07
    淘宝
    0.07
     CSI
    0.07
     responsible
    0.07
     hi
    0.07
    chtig
    0.07
    Activations Density 0.021%

    No Known Activations