© 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. 50240
    Prev
    Next
    INDEX
    Explanations

    say "ending in za/ze"

    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
    lur
    -0.08
     environnement
    -0.08
    riculture
    -0.07
     automatis
    -0.07
    may
    -0.07
     após
    -0.07
    ractions
    -0.07
    ânico
    -0.07
     RH
    -0.07
     steering
    -0.07
    POSITIVE LOGITS
    za
    0.12
    zial
    0.11
    ziale
    0.10
    ZA
    0.09
    zuela
    0.09
    Za
    0.09
    zien
    0.08
    Sa
    0.08
    ándonos
    0.08
    zi
    0.08
    Activations Density 0.001%

    No Known Activations