© 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. 70436
    Prev
    Next
    INDEX
    Explanations

    websites

    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
     prioritize
    -0.08
     anesthesia
    -0.08
    き
    -0.08
    IDGE
    -0.08
     rumors
    -0.07
    shoe
    -0.07
    �
    -0.07
    -wide
    -0.07
     شکن
    -0.07
     progressively
    -0.07
    POSITIVE LOGITS
     สำ
    0.08
     investigated
    0.08
    /S
    0.08
     solicitado
    0.08
    Tasks
    0.08
     നിന്നും
    0.07
    /App
    0.07
     Paypal
    0.07
     اک
    0.07
     Used
    0.07
    Activations Density 0.000%

    No Known Activations