© 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. 29693
    Prev
    Next
    INDEX
    Explanations

    creating references

    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
     Cobra
    -0.08
     Scoop
    -0.08
     ergonom
    -0.08
    _height
    -0.08
    mainder
    -0.08
     liebe
    -0.08
     leash
    -0.08
    Ingrese
    -0.08
     negate
    -0.07
    awatan
    -0.07
    POSITIVE LOGITS
     citations
    0.12
     citar
    0.12
     bibliography
    0.11
     cites
    0.11
     citation
    0.10
     citing
    0.10
     credible
    0.09
     cite
    0.09
     Citation
    0.09
    引用
    0.09
    Activations Density 0.031%

    No Known Activations