© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-RESID-POST-AA
    11. 13093
    Prev
    Next
    INDEX
    Explanations

    hyphens and colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jac
    -0.08
     formidable
    -0.08
    Couldn't
    -0.08
     הצל
    -0.07
    ələr
    -0.07
     �
    -0.07
    Nl
    -0.07
    ən
    -0.07
    ı
    -0.07
     Contains
    -0.07
    POSITIVE LOGITS
     bab
    0.07
    Mil
    0.07
     bom
    0.07
     clutch
    0.07
    くら
    0.07
    glass
    0.07
    จะ
    0.07
     ni
    0.07
     પ્ર
    0.07
    资料
    0.07
    Activations Density 0.525%

    No Known Activations