© 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. 30191
    Prev
    Next
    INDEX
    Explanations

    cloud

    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
    stelle
    -0.08
    digits
    -0.08
     Reduc
    -0.07
     Costume
    -0.07
    Valve
    -0.07
    \Console
    -0.07
     deducted
    -0.07
     Father
    -0.07
    irre
    -0.07
    -Reg
    -0.07
    POSITIVE LOGITS
    対応
    0.09
     sick
    0.08
     Gemini
    0.08
     namar
    0.08
     kube
    0.08
    生态
    0.08
    andre
    0.08
     interoper
    0.08
     કુ
    0.08
    -wow
    0.08
    Activations Density 0.002%

    No Known Activations