© 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. 45248
    Prev
    Next
    INDEX
    Explanations

    instructions and comparisons

    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
     Wars
    -0.08
    ERM
    -0.08
     بعدما
    -0.08
     giúp
    -0.07
     merupakan
    -0.07
     reales
    -0.07
     inté
    -0.07
    134
    -0.07
     nhé
    -0.07
    ंश
    -0.07
    POSITIVE LOGITS
    에서는
    0.10
     alike
    0.10
    /count
    0.08
     бывает
    0.08
    では
    0.08
    情侣
    0.08
    abase
    0.08
    .segment
    0.08
    005
    0.08
     puhul
    0.08
    Activations Density 0.111%

    No Known Activations