© 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. 5710
    Prev
    Next
    INDEX
    Explanations

    Sol

    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
     livest
    -0.08
    алее
    -0.08
    aws
    -0.08
    еге
    -0.07
    хэн
    -0.07
    rscheinlich
    -0.07
    桶
    -0.07
    ानि
    -0.07
     aws
    -0.07
    ellten
    -0.07
    POSITIVE LOGITS
    stice
    0.17
    түстік
    0.16
    UTIONS
    0.16
    uções
    0.15
    uzioni
    0.15
    uble
    0.15
    uciones
    0.15
    idaire
    0.15
    itary
    0.15
    usyon
    0.15
    Activations Density 0.031%

    No Known Activations