© 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. 96637
    Prev
    Next
    INDEX
    Explanations

    уд

    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
     crisp
    -0.08
    iyalar
    -0.08
    bedarf
    -0.08
     সাক্ষ
    -0.08
    'instant
    -0.08
    porary
    -0.07
    .heading
    -0.07
    িত্য
    -0.07
    icast
    -0.07
     heading
    -0.07
    POSITIVE LOGITS
    ары
    0.10
    лин
    0.09
     rz
    0.09
    зел
    0.08
    ель
    0.08
    лини
    0.08
    алась
    0.08
    ались
    0.08
     elt
    0.08
    ался
    0.08
    Activations Density 0.001%

    No Known Activations