© 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. 31095
    Prev
    Next
    INDEX
    Explanations

    Beginning of conversations/rewrites

    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
     coordinated
    -0.07
     markers
    -0.07
     CHECK
    -0.07
     checked
    -0.07
     signe
    -0.07
     promising
    -0.07
     Rece
    -0.07
     synchronized
    -0.07
     nearest
    -0.07
    ङ
    -0.07
    POSITIVE LOGITS
    (original
    0.11
     оригин
    0.11
    Original
    0.10
     ursprüng
    0.10
     originale
    0.10
     shortcomings
    0.10
    original
    0.09
     oorspronkelijke
    0.09
     original
    0.09
    _original
    0.09
    Activations Density 0.085%

    No Known Activations