© 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. 69983
    Prev
    Next
    INDEX
    Explanations

    reference

    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
     Alley
    -0.08
    Deg
    -0.08
    �
    -0.08
     Gilbert
    -0.08
     retard
    -0.07
     nut
    -0.07
    akin
    -0.07
    Bal
    -0.07
    ’t
    -0.07
    nut
    -0.07
    POSITIVE LOGITS
     creating
    0.07
     pup
    0.07
     ith
    0.07
    渡
    0.07
     kuinka
    0.07
     conven
    0.07
    erend
    0.07
    buk
    0.07
    望
    0.07
    ა
    0.07
    Activations Density 0.026%

    No Known Activations