© 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. 50091
    Prev
    Next
    INDEX
    Explanations

    period

    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
    .tap
    -0.08
     probabil
    -0.08
     penetrate
    -0.08
     penetr
    -0.08
    tap
    -0.07
    Tap
    -0.07
     guna
    -0.07
    idity
    -0.07
    onya
    -0.07
    aderen
    -0.07
    POSITIVE LOGITS
    aird
    0.08
     critiques
    0.08
     IR
    0.07
     critique
    0.07
    ecut
    0.07
    ashire
    0.07
     chor
    0.07
    естер
    0.07
     Crit
    0.07
     Escorte
    0.07
    Activations Density 0.000%

    No Known Activations