© 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. 19-RESID-POST-AA
    11. 18405
    Prev
    Next
    INDEX
    Explanations

    Winning/defeating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alala
    -0.08
     contemplation
    -0.08
    areness
    -0.07
    nol
    -0.07
    Coment
    -0.07
     고민
    -0.07
    _exist
    -0.07
    allow
    -0.07
    =id
    -0.07
     adaptations
    -0.07
    POSITIVE LOGITS
     surpass
    0.21
     defeating
    0.20
     beating
    0.19
     overpower
    0.19
     beat
    0.19
     superar
    0.18
     outperform
    0.18
     превос
    0.17
     beats
    0.17
     surpassed
    0.17
    Activations Density 0.022%

    No Known Activations