© 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. 50623
    Prev
    Next
    INDEX
    Explanations

    Lesions

    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
     sugars
    -0.08
     viruses
    -0.08
     virus
    -0.08
     hemen
    -0.08
     ciência
    -0.08
    virus
    -0.07
    @↵↵
    -0.07
    GRESS
    -0.07
    Inte
    -0.07
    andang
    -0.07
    POSITIVE LOGITS
     lesiones
    0.18
     lesions
    0.17
     Les
    0.16
     lesión
    0.16
     lesion
    0.15
    Les
    0.15
     Läs
    0.14
     lés
    0.14
     les
    0.13
    -les
    0.12
    Activations Density 0.012%

    No Known Activations