© 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. 11-RESID-POST-AA
    11. 30126
    Prev
    Next
    INDEX
    Explanations

    Network performance tools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     компакт
    -0.09
     compacto
    -0.09
     compacte
    -0.09
    compact
    -0.09
     diaspora
    -0.08
     комп
    -0.08
     kere
    -0.08
     compact
    -0.08
    )add
    -0.08
     asistentes
    -0.08
    POSITIVE LOGITS
    測
    0.09
    Sender
    0.08
     Conduct
    0.08
     Sender
    0.08
     fla
    0.08
     empir
    0.08
    -web
    0.08
    _sender
    0.08
     negotiated
    0.08
     empirical
    0.08
    Activations Density 0.004%

    No Known Activations