© 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. 19-RESID-POST-AA
    11. 102947
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pedras
    -0.09
     fonte
    -0.08
    Meu
    -0.08
    Typeface
    -0.08
     lose
    -0.08
     weer
    -0.08
     campo
    -0.08
     piedras
    -0.07
     fuente
    -0.07
    ourced
    -0.07
    POSITIVE LOGITS
     చిన్న
    0.09
     ಸುಮಾರು
    0.09
     tiny
    0.09
     أغ
    0.08
     ചെറിയ
    0.08
    ingles
    0.08
     %.
    0.08
     geringe
    0.08
    Approximately
    0.08
     barely
    0.08
    Activations Density 0.026%

    No Known Activations