© 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 EvalsExportsinterp-engineNEWAPI 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. 111036
    Prev
    Next
    INDEX
    Explanations

    galaxy formation, gas accretion

    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
    숙
    -0.08
    协会
    -0.07
    association
    -0.07
    depth
    -0.07
     flair
    -0.07
    Association
    -0.07
    control
    -0.07
     frères
    -0.07
     map
    -0.07
     Association
    -0.07
    POSITIVE LOGITS
    瓶
    0.08
    מים
    0.08
     להע
    0.07
    (inputs
    0.07
     mgbanwe
    0.07
     идти
    0.07
     идут
    0.07
     timeless
    0.07
    angles
    0.07
     informs
    0.07
    Activations Density 0.000%

    No Known Activations