© 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. 23-RESID-POST-AA
    11. 49142
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     keess
    -0.09
    lichkeiten
    -0.08
    伙
    -0.08
     handling
    -0.08
     logged
    -0.08
    ðum
    -0.08
    Tracked
    -0.08
    ғына
    -0.07
    嫌
    -0.07
     messed
    -0.07
    POSITIVE LOGITS
    ative
    0.20
    ительная
    0.20
    ительный
    0.19
    ительную
    0.19
    ительного
    0.19
    ительные
    0.18
    ительное
    0.18
    ATIVE
    0.18
    ительными
    0.18
    ительной
    0.18
    Activations Density 0.098%

    No Known Activations