© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64010
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    ewa
    -0.08
    努力
    -0.08
     leid
    -0.07
     Zürich
    -0.07
     zabr
    -0.07
     uncover
    -0.07
     Fahrr
    -0.07
    ników
    -0.07
     engagé
    -0.07
     pest
    -0.07
    POSITIVE LOGITS
     bursts
    0.11
     burst
    0.09
     flashes
    0.09
     spikes
    0.08
     pulses
    0.08
    burst
    0.08
     impulses
    0.08
    Impulse
    0.08
     timed
    0.08
    .repeat
    0.08
    Activations Density 0.008%

    No Known Activations