© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48019
    Prev
    Next
    INDEX
    Explanations

    say "لا word"

    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
    thon
    -0.08
     djel
    -0.07
     Smile
    -0.07
    패
    -0.07
     Myth
    -0.07
    as
    -0.07
     PARTY
    -0.07
    زان
    -0.07
    myp
    -0.07
     패
    -0.07
    POSITIVE LOGITS
     height
    0.08
    (pos
    0.08
     pos
    0.07
     mismatch
    0.07
     interchange
    0.07
    .pos
    0.07
    атр
    0.07
    oukset
    0.07
     ressalt
    0.07
     potencia
    0.07
    Activations Density 0.005%

    No Known Activations