© 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. 19-RESID-POST-AA
    11. 19124
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }
    -0.07
    ۔
    -0.07
    acola
    -0.07
    :\
    -0.07
    arem
    -0.07
    ।
    -0.07
    ajj
    -0.07
    ieni
    -0.06
    ：
    -0.06
    ataa
    -0.06
    POSITIVE LOGITS
     Deshalb
    0.37
     hence
    0.32
     ولذلك
    0.32
     Daarom
    0.31
     এজন
    0.31
     deshalb
    0.31
     derfor
    0.31
     Hence
    0.31
     daarom
    0.30
     därför
    0.30
    Activations Density 0.060%

    No Known Activations