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. 11691
    Prev
    Next
    INDEX
    Explanations

    contest

    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
     corona
    -0.08
    Ved
    -0.08
     Tasche
    -0.07
     വ്യ
    -0.07
    வே
    -0.07
     бос
    -0.07
    emd
    -0.07
     NAM
    -0.07
     свобод
    -0.07
    VAR
    -0.07
    POSITIVE LOGITS
    -winning
    0.09
    ued
    0.08
     Ba
    0.08
    iveness
    0.08
    ुअ
    0.08
     debuted
    0.08
     photoc
    0.08
     Gunn
    0.07
     uphold
    0.07
     Christoph
    0.07
    Activations Density 0.012%

    No Known Activations