© 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. 110787
    Prev
    Next
    INDEX
    Explanations

    enabling settings

    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
     estil
    -0.09
    Sty
    -0.08
     অসম
    -0.08
    новения
    -0.07
     Styling
    -0.07
    .reject
    -0.07
    ൂപ
    -0.07
     Editorial
    -0.07
    �
    -0.07
     різ
    -0.07
    POSITIVE LOGITS
     enabling
    0.09
     conducive
    0.09
     enabled
    0.08
     Johansson
    0.08
    .enable
    0.08
     desblo
    0.08
     expressly
    0.08
    	enable
    0.08
     accessible
    0.08
     extrait
    0.08
    Activations Density 0.026%

    No Known Activations