© 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. 111510
    Prev
    Next
    INDEX
    Explanations

    remember

    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
     schaut
    -0.09
     சக
    -0.08
    pping
    -0.08
     hosi
    -0.08
    “My
    -0.08
     ежегод
    -0.08
     Пок
    -0.08
     mahs
    -0.08
    “I
    -0.08
     катары
    -0.08
    POSITIVE LOGITS
    X
    0.07
     tight
    0.07
    osomes
    0.07
     tort
    0.07
    _
    0.07
     governed
    0.07
     preciso
    0.07
    宴
    0.07
     RA
    0.07
    ڪٽ
    0.07
    Activations Density 0.002%

    No Known Activations