© 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 EvalsExportsAPI 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. 69193
    Prev
    Next
    INDEX
    Explanations

    nude bath and farts

    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
     anymore
    -0.08
     bore
    -0.08
    Extended
    -0.07
    িযোগ
    -0.07
     toán
    -0.07
     essential
    -0.07
    。例如
    -0.07
     itt
    -0.07
    имых
    -0.07
     requiring
    -0.07
    POSITIVE LOGITS
    ([^
    0.08
    severity
    0.08
     камера
    0.07
    avours
    0.07
     vill
    0.07
     compagn
    0.07
     Severe
    0.07
    scenario
    0.07
    หัว
    0.07
    vemos
    0.07
    Activations Density 0.036%

    No Known Activations