© 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. 48048
    Prev
    Next
    INDEX
    Explanations

    say "if" ending

    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
    iculares
    -0.09
    ícul
    -0.08
    ipid
    -0.08
    icular
    -0.08
    icers
    -0.08
    resión
    -0.08
    icem
    -0.08
    icacité
    -0.08
     ICT
    -0.08
    netic
    -0.08
    POSITIVE LOGITS
    ándonos
    0.08
    er
    0.08
     ود
    0.08
     erase
    0.08
    ate
    0.08
    ien
    0.08
     सत
    0.07
     samband
    0.07
     mann
    0.07
    ivati
    0.07
    Activations Density 0.001%

    No Known Activations