© 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. 96547
    Prev
    Next
    INDEX
    Explanations

    vitamins

    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
    strained
    -0.08
    Tod
    -0.08
    εδ
    -0.08
    ומות
    -0.08
    akr
    -0.08
    FINITE
    -0.07
     provavelmente
    -0.07
    -ton
    -0.07
     calf
    -0.07
    agasy
    -0.07
    POSITIVE LOGITS
    िने
    0.09
    ेश
    0.08
     scheduling
    0.08
     بی
    0.07
     Shader
    0.07
    ಿವ
    0.07
    ેશ
    0.07
     datas
    0.07
     neutr
    0.07
     shading
    0.07
    Activations Density 0.001%

    No Known Activations