© 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. 49233
    Prev
    Next
    INDEX
    Explanations

    �

    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
     langage
    -0.08
     linguagem
    -0.08
    离
    -0.07
     reverse
    -0.07
    ду
    -0.07
    arnation
    -0.07
    ָ
    -0.07
    ガ
    -0.07
     language
    -0.07
     Stu
    -0.07
    POSITIVE LOGITS
    �
    0.11
    _tt
    0.08
    thy
    0.08
    (train
    0.08
     Иск
    0.08
    .tight
    0.08
     arall
    0.08
     ऊपर
    0.08
    aneq
    0.07
    .ceil
    0.07
    Activations Density 0.000%

    No Known Activations