© 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. 110809
    Prev
    Next
    INDEX
    Explanations

    are

    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
    icato
    -0.09
    *))
    -0.08
     imperme
    -0.07
    맞
    -0.07
     것도
    -0.07
    straight
    -0.07
    ']?>
    -0.07
    (FILE
    -0.07
     Ack
    -0.07
     Alder
    -0.07
    POSITIVE LOGITS
     advise
    0.08
     рады
    0.08
     advising
    0.08
     adjusts
    0.08
    ער
    0.07
     Ye
    0.07
     stolz
    0.07
     advised
    0.07
     hah
    0.07
     Нов
    0.07
    Activations Density 0.119%

    No Known Activations