© 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. 113254
    Prev
    Next
    INDEX
    Explanations

    prompts

    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
     prosecut
    -0.08
    ?),
    -0.08
     prosecution
    -0.08
     stom
    -0.08
     interrog
    -0.08
     marijuana
    -0.08
     prosecutors
    -0.07
     diagnose
    -0.07
     Jésus
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     '\\
    0.08
     benutzt
    0.08
     Sino
    0.07
     '\
    0.07
     каб
    0.07
     привед
    0.07
     feront
    0.07
     ieder
    0.07
     estén
    0.07
    дың
    0.07
    Activations Density 0.003%

    No Known Activations