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

    Neuronpedia

    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. 94629
    Prev
    Next
    INDEX
    Explanations

    benefits of making a choice

    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
    iri
    -0.08
     ranc
    -0.08
    ات
    -0.07
    ть
    -0.07
    wania
    -0.07
     finishing
    -0.07
    Du
    -0.07
    -ri
    -0.07
    pé
    -0.07
     Uri
    -0.07
    POSITIVE LOGITS
     estaria
    0.10
     estarão
    0.10
     unknow
    0.09
     будете
    0.09
    _ev
    0.09
     inadvertently
    0.08
    대한
    0.08
     estás
    0.08
     �
    0.08
     خواهید
    0.08
    Activations Density 0.156%

    No Known Activations