© 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. 26509
    Prev
    Next
    INDEX
    Explanations

    separators in lists/tables

    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
    -0.08
    ший
    -0.07
    段
    -0.07
    cab
    -0.07
    okw
    -0.07
     neka
    -0.07
     предпочт
    -0.07
    .selection
    -0.07
     нед
    -0.07
    ші
    -0.07
    POSITIVE LOGITS
     Thankfully
    0.11
     Fortunately
    0.11
     constantemente
    0.10
     zusätzlichen
    0.10
     painstaking
    0.10
     Luckily
    0.10
     constantly
    0.09
     bothered
    0.09
    Luckily
    0.09
    才能
    0.09
    Activations Density 0.128%
    No Known Activations