© 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. 111539
    Prev
    Next
    INDEX
    Explanations

    hopeless

    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
    Everybody
    -0.08
    ۾
    -0.08
     eins
    -0.08
     음
    -0.08
    нож
    -0.08
     اللح
    -0.08
     неё
    -0.08
     ағ
    -0.08
     शक्ति
    -0.08
     conséquent
    -0.08
    POSITIVE LOGITS
    haft
    0.08
    664
    0.07
    pun
    0.07
    Tra
    0.07
    857
    0.07
    place
    0.07
     wok
    0.07
     jurisdiction
    0.07
    CALE
    0.07
    াইট
    0.07
    Activations Density 0.002%

    No Known Activations