© 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. 19-RESID-POST-AA
    11. 18851
    Prev
    Next
    INDEX
    Explanations

    alternative

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quidem
    -0.08
    ayana
    -0.07
     omhoog
    -0.07
    inning
    -0.07
    êm
    -0.07
    inggi
    -0.07
    uttet
    -0.07
    edevším
    -0.07
     komst
    -0.06
     ј
    -0.06
    POSITIVE LOGITS
     alternative
    0.64
     alternatives
    0.62
     альтернатив
    0.59
     alternativas
    0.59
    Alternative
    0.58
     Alternative
    0.57
    alternative
    0.57
     alternativa
    0.56
     alternatif
    0.56
     Alternatives
    0.56
    Activations Density 0.172%

    No Known Activations