© 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. 95377
    Prev
    Next
    INDEX
    Explanations

    FYI

    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
     gam
    -0.07
     penetrate
    -0.07
     뛰
    -0.07
     kome
    -0.07
    unity
    -0.07
     �
    -0.07
     Wirtschafts
    -0.07
    culas
    -0.07
    avati
    -0.07
    phony
    -0.07
    POSITIVE LOGITS
    ちなみに
    0.10
    .Note
    0.10
    .note
    0.10
     reassurance
    0.10
     alvast
    0.09
     noting
    0.09
     precaution
    0.09
     reminder
    0.09
     reminding
    0.09
     courtesy
    0.08
    Activations Density 0.055%

    No Known Activations