© 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. 19-RESID-POST-AA
    11. 18567
    Prev
    Next
    INDEX
    Explanations

    theme

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DHL
    -0.08
    cuda
    -0.07
    RTX
    -0.07
     Erste
    -0.07
     देना
    -0.07
     prête
    -0.07
     लगी
    -0.07
    dsn
    -0.07
    gebnis
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     park
    0.18
     parks
    0.16
    park
    0.16
    Park
    0.15
     Park
    0.15
     पार्क
    0.13
     парк
    0.13
     Parks
    0.12
    elves
    0.12
    parks
    0.12
    Activations Density 0.014%

    No Known Activations