© 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. 112582
    Prev
    Next
    INDEX
    Explanations

    Lenovo ThinkPad X1

    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
    ující
    -0.08
     fraternity
    -0.08
    values
    -0.08
    ār
    -0.08
    primary
    -0.08
     dě
    -0.08
    crt
    -0.08
    unk
    -0.08
     predominant
    -0.08
    ujete
    -0.08
    POSITIVE LOGITS
     stiffness
    0.08
    Stencil
    0.07
    Stamp
    0.07
     Bayesian
    0.07
     shelf
    0.07
     Skeleton
    0.07
     Converse
    0.07
     utile
    0.07
     useful
    0.07
    .Bean
    0.07
    Activations Density 0.001%

    No Known Activations