© 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. 63115
    Prev
    Next
    INDEX
    Explanations

    +

    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
     infatti
    -0.08
    乎
    -0.08
     sebesar
    -0.07
     terlebih
    -0.07
     terd
    -0.07
    ਿਗ
    -0.07
     eikä
    -0.07
     linewidth
    -0.07
     puntu
    -0.07
    年轻
    -0.07
    POSITIVE LOGITS
    mdash
    0.09
    NC
    0.09
    ndash
    0.09
    /or
    0.09
    /ou
    0.08
    nbsp
    0.08
     importantly
    0.07
     നിർ
    0.07
     transport
    0.07
    transport
    0.07
    Activations Density 0.033%

    No Known Activations