© 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. 110565
    Prev
    Next
    INDEX
    Explanations

    underscore

    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
    返品
    -0.09
    iteurs
    -0.09
    归
    -0.09
    帰
    -0.09
     noticias
    -0.08
     Mitchell
    -0.08
     мире
    -0.08
     싶은
    -0.08
     �
    -0.08
     kakhulu
    -0.08
    POSITIVE LOGITS
     triangular
    0.08
    ตรี
    0.08
    tri
    0.07
     trig
    0.07
     pouvons
    0.07
     multiplier
    0.07
     देकर
    0.07
    цо
    0.07
    (form
    0.07
     transc
    0.07
    Activations Density 0.007%

    No Known Activations