© 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. 64242
    Prev
    Next
    INDEX
    Explanations

    square roots

    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
     군
    -0.08
     אד
    -0.08
    ერგ
    -0.08
     hemorr
    -0.08
     Bleu
    -0.08
     argumentative
    -0.08
     okoli
    -0.08
     monstrous
    -0.08
     arribar
    -0.08
     Herbs
    -0.08
    POSITIVE LOGITS
     sqrt
    0.07
    √
    0.07
    故
    0.07
     certificate
    0.07
    ascending
    0.07
    sqrt
    0.07
     reconstruct
    0.07
     troph
    0.07
    Adv
    0.07
    qrt
    0.07
    Activations Density 0.033%

    No Known Activations