© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31075
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    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
    irio
    -0.08
     unsuccess
    -0.08
    ੂਰ
    -0.08
     ressemble
    -0.07
     році
    -0.07
     Kidney
    -0.07
     sac
    -0.07
    ровать
    -0.07
     contiguous
    -0.07
    unkt
    -0.07
    POSITIVE LOGITS
     चाहे
    0.11
     سواء
    0.10
    든
    0.10
     Whether
    0.09
    Whether
    0.08
     klær
    0.08
     gowns
    0.08
     디
    0.08
     dramas
    0.08
     maupun
    0.08
    Activations Density 0.071%

    No Known Activations