© 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. 11-RESID-POST-AA
    11. 70431
    Prev
    Next
    INDEX
    Explanations

    correcting math misconceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    likely
    -0.08
    lán
    -0.08
    fortunately
    -0.07
    orous
    -0.07
    oretical
    -0.07
     daß
    -0.07
    -0.07
    RF
    -0.07
    Tema
    -0.07
    -full
    -0.07
    POSITIVE LOGITS
     incorrectly
    0.12
     wrongly
    0.10
     errone
    0.10
     mistakenly
    0.10
     невер
    0.10
     miscon
    0.09
     wrong
    0.09
     misunderstood
    0.09
     confused
    0.09
     misunderstanding
    0.09
    Activations Density 0.060%
    No Known Activations