© 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. 110428
    Prev
    Next
    INDEX
    Explanations

    pin

    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
     bureau
    -0.08
     stated
    -0.08
    Plat
    -0.07
     люб
    -0.07
     rab
    -0.07
    564
    -0.07
    �
    -0.07
     కావ
    -0.07
    拜
    -0.07
    မွ
    -0.07
    POSITIVE LOGITS
     dug
    0.10
    brew
    0.08
    disc
    0.07
    Disc
    0.07
    omial
    0.07
     dig
    0.07
    -outline
    0.07
    วิ
    0.07
    击
    0.07
     зрения
    0.07
    Activations Density 0.007%

    No Known Activations