© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 49750
    Prev
    Next
    INDEX
    Explanations

    qqu

    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
     cérebro
    -0.09
    id
    -0.09
    çou
    -0.09
     pouvoirs
    -0.08
    linux
    -0.08
     gâteau
    -0.08
    draw
    -0.08
    ça
    -0.08
    axa
    -0.08
    sects
    -0.08
    POSITIVE LOGITS
    Ade
    0.09
     blanca
    0.08
    白
    0.08
    тон
    0.08
    .wh
    0.08
     җит
    0.08
     ಬಾರಿ
    0.08
    utab
    0.07
     blancos
    0.07
     putih
    0.07
    Activations Density 0.001%

    No Known Activations