© 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. 54709
    Prev
    Next
    INDEX
    Explanations

    character names

    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
    cro
    -0.10
    棒
    -0.08
    olta
    -0.08
     Article
    -0.07
    YN
    -0.07
    лоб
    -0.07
    olos
    -0.07
    Angular
    -0.07
    126
    -0.07
    290
    -0.07
    POSITIVE LOGITS
     Gh
    0.08
    ，这是
    0.08
     Thompson
    0.08
     helped
    0.08
     spear
    0.08
     safegu
    0.08
    (info
    0.07
     sharpen
    0.07
    åller
    0.07
     aka
    0.07
    Activations Density 0.036%

    No Known Activations