© 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. 94805
    Prev
    Next
    INDEX
    Explanations

    Reasons and explanations

    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
     confessed
    -0.08
    -sac
    -0.07
    635
    -0.07
     confess
    -0.07
     espada
    -0.07
     Bartlett
    -0.07
    enever
    -0.07
     sac
    -0.07
    Å
    -0.07
    ư
    -0.07
    POSITIVE LOGITS
    这一
    0.10
    .Pos
    0.08
     ipo
    0.08
     LY
    0.08
    到底
    0.08
    .Lbl
    0.08
    Demo
    0.07
    compact
    0.07
     desse
    0.07
    .Read
    0.07
    Activations Density 0.374%

    No Known Activations