© 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. 49194
    Prev
    Next
    INDEX
    Explanations

    non-English

    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
    实现
    -0.08
    (IP
    -0.07
    提供
    -0.07
    ("'
    -0.07
     realization
    -0.07
    作为
    -0.07
    (IF
    -0.07
    을
    -0.07
    (function
    -0.07
     제공
    -0.07
    POSITIVE LOGITS
    apos
    0.09
    abil
    0.09
    ardır
    0.09
    arns
    0.09
     jälkeen
    0.08
     ṣugbọn
    0.08
    ktiv
    0.08
     drugih
    0.08
     andra
    0.08
     іншых
    0.08
    Activations Density 0.937%

    No Known Activations