© 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. 23-RESID-POST-AA
    11. 51196
    Prev
    Next
    INDEX
    Explanations

    Int

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thirst
    -0.07
     Sprach
    -0.07
     aquests
    -0.07
     installments
    -0.07
    Elapsed
    -0.07
     políticas
    -0.07
    leer
    -0.07
     estos
    -0.07
     lower
    -0.07
    -Sm
    -0.07
    POSITIVE LOGITS
     muamua
    0.08
     faf
    0.08
    сион
    0.08
    даў
    0.08
     ერთი
    0.08
     مقدار
    0.08
     sx
    0.08
    IVERS
    0.07
     విషయం
    0.07
     Fisk
    0.07
    Activations Density 0.000%

    No Known Activations