© 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 EvalsExportsinterp-engineNEWAPI 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. 51633
    Prev
    Next
    INDEX
    Explanations

    Spanish words

    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
     база
    -0.09
    ARA
    -0.08
    ahia
    -0.08
    essaa
    -0.08
    ема
    -0.08
    apia
    -0.07
    ienta
    -0.07
     pudesse
    -0.07
    uaa
    -0.07
    ети
    -0.07
    POSITIVE LOGITS
     calientes
    0.14
     vendas
    0.13
     valores
    0.13
     ajustes
    0.13
     mejores
    0.13
     plantes
    0.13
     uses
    0.12
     selles
    0.12
     limites
    0.12
     cites
    0.12
    Activations Density 0.008%

    No Known Activations