© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 113522
    Prev
    Next
    INDEX
    Explanations

    touch

    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
     finis
    -0.08
    책
    -0.07
    ride
    -0.07
     delicioso
    -0.07
    awasan
    -0.07
     alimentar
    -0.07
    ije
    -0.07
     fascinating
    -0.07
     lamin
    -0.07
     delicios
    -0.07
    POSITIVE LOGITS
     સંપર્ક
    0.11
    联系
    0.11
     outreach
    0.11
     জানান
    0.11
     μαζί
    0.10
     контакт
    0.10
    骚
    0.10
    交流
    0.10
    .contact
    0.10
     연락
    0.10
    Activations Density 0.079%

    No Known Activations