© 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. 19-RESID-POST-AA
    11. 102499
    Prev
    Next
    INDEX
    Explanations

    Recover

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spirits
    -0.09
     stagnant
    -0.09
    inish
    -0.09
     изменение
    -0.08
    departure
    -0.08
     aprecia
    -0.08
     �
    -0.08
     өзгер
    -0.08
     rebellious
    -0.08
     ferv
    -0.08
    POSITIVE LOGITS
     procedures
    0.11
     mechanisms
    0.11
     capabilities
    0.11
    机制
    0.11
     capability
    0.11
     সক্ষম
    0.10
    abilidad
    0.10
    ability
    0.10
     logic
    0.10
    流程
    0.10
    Activations Density 0.007%

    No Known Activations