© 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. 3-RESID-POST-AA
    11. 1473
    Prev
    Next
    INDEX
    Explanations

    articles/pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fran
    -0.09
     Mab
    -0.08
    hetical
    -0.08
    ieli
    -0.08
     Robinson
    -0.08
     حس
    -0.08
     Vid
    -0.07
     Unter
    -0.07
     Thi
    -0.07
    Elm
    -0.07
    POSITIVE LOGITS
     lá
    0.08
     andando
    0.07
    .Flags
    0.07
     nada
    0.07
     aficionados
    0.07
    Dealer
    0.07
    Affinity
    0.07
    Normal
    0.07
    라는
    0.07
     ا
    0.07
    Activations Density 0.025%

    No Known Activations