© 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. 18686
    Prev
    Next
    INDEX
    Explanations

    �

    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
     invitation
    -0.08
     похож
    -0.08
     dụng
    -0.08
    ’air
    -0.07
    -air
    -0.07
     posibilidad
    -0.07
    лова
    -0.07
    -of
    -0.07
     Frauen
    -0.07
    utions
    -0.07
    POSITIVE LOGITS
    ity
    0.10
    තාව
    0.10
    坡
    0.09
    šo
    0.09
    ेख
    0.08
     implement
    0.08
    angulo
    0.08
    aport
    0.08
     tarap
    0.08
    angle
    0.08
    Activations Density 0.001%

    No Known Activations