© 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. 113737
    Prev
    Next
    INDEX
    Explanations

    method

    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
     braid
    -0.09
     braided
    -0.08
     قائم
    -0.08
     foliage
    -0.08
     λ
    -0.08
     thiếu
    -0.07
     teniendo
    -0.07
     থেকে
    -0.07
     wedge
    -0.07
    chain
    -0.07
    POSITIVE LOGITS
     enctype
    0.10
     maxlength
    0.08
    реж
    0.08
    maxlength
    0.07
     vals
    0.07
    iframe
    0.07
    301
    0.07
     soul
    0.07
    -horizontal
    0.07
     unforgettable
    0.07
    Activations Density 0.001%

    No Known Activations