© 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. 63057
    Prev
    Next
    INDEX
    Explanations

    s

    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
    shown
    -0.09
    sp
    -0.08
    型
    -0.08
    多数
    -0.08
     benötigt
    -0.08
     implying
    -0.07
     പാല
    -0.07
     ausw
    -0.07
    shoe
    -0.07
     dubb
    -0.07
    POSITIVE LOGITS
     Synopsis
    0.08
    lais
    0.08
     pró
    0.08
    forth
    0.08
     полный
    0.08
     Franco
    0.07
     neuer
    0.07
     Sec
    0.07
     memorandum
    0.07
     glimps
    0.07
    Activations Density 0.017%

    No Known Activations