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

    Neuronpedia

    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. 25144
    Prev
    Next
    INDEX
    Explanations

    generating creative image descriptions

    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
     marx
    -0.08
     obč
    -0.08
     Bartlett
    -0.08
    (variable
    -0.08
     psychiatric
    -0.08
    ентар
    -0.08
     Brent
    -0.08
     pagpap
    -0.08
     disagreements
    -0.07
     TMP
    -0.07
    POSITIVE LOGITS
    Uy
    0.08
    -remove
    0.08
     mogao
    0.08
     wardrobes
    0.07
    moon
    0.07
     wore
    0.07
     �
    0.07
     wearer
    0.07
    yel
    0.07
     wears
    0.07
    Activations Density 0.002%

    No Known Activations