© 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. 64160
    Prev
    Next
    INDEX
    Explanations

    brushed

    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
     pagos
    -0.08
    onc
    -0.08
     malaria
    -0.08
     revise
    -0.07
    blocks
    -0.07
    गर
    -0.07
    revision
    -0.07
    owitz
    -0.07
     revision
    -0.07
    ারণ
    -0.07
    POSITIVE LOGITS
     yarn
    0.09
     Edelstahl
    0.08
     دنبال
    0.08
     subdued
    0.08
    후
    0.08
     Adams
    0.08
     Rustic
    0.08
     pastel
    0.08
     rustic
    0.08
     waterfront
    0.07
    Activations Density 0.005%

    No Known Activations