© 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. 50110
    Prev
    Next
    INDEX
    Explanations

    Yoga or Spanish

    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
    mě
    -0.09
    -nav
    -0.08
    imeter
    -0.08
    -кон
    -0.08
    লার
    -0.08
    WRITE
    -0.08
    mailer
    -0.08
    piar
    -0.08
    -rating
    -0.08
    ्काल
    -0.08
    POSITIVE LOGITS
    edere
    0.08
     taşı
    0.08
     cow
    0.08
     Girl
    0.08
     Guy
    0.08
     U
    0.08
     PBS
    0.07
    U
    0.07
     IU
    0.07
     transporte
    0.07
    Activations Density 0.002%

    No Known Activations