© 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. 114159
    Prev
    Next
    INDEX
    Explanations

    translate

    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
    ration
    -0.08
     जे
    -0.08
     Microsoft's
    -0.08
     справ
    -0.07
     defeated
    -0.07
     되고
    -0.07
     gerek
    -0.07
     unga
    -0.07
    zilla
    -0.07
    43
    -0.07
    POSITIVE LOGITS
    Autoresizing
    0.09
    Kut
    0.08
    ការ�
    0.08
    difficulty
    0.08
     excitement
    0.08
    ело
    0.08
    Gig
    0.08
    ما
    0.08
     actionable
    0.08
     mastery
    0.07
    Activations Density 0.026%

    No Known Activations