© 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. 8010
    Prev
    Next
    INDEX
    Explanations

    less than

    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
     aumento
    -0.09
     augmenté
    -0.08
    .for
    -0.08
     tough
    -0.08
     erhöhen
    -0.08
     agrav
    -0.08
     aumentado
    -0.08
     Shaft
    -0.08
     thick
    -0.08
     augmented
    -0.07
    POSITIVE LOGITS
     tussen
    0.09
     murderer
    0.08
    Leer
    0.08
    lfriend
    0.07
    etween
    0.07
    กัน
    0.07
    比
    0.07
     unbeaten
    0.07
    Nog
    0.07
     kept
    0.07
    Activations Density 0.016%

    No Known Activations