© 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. 23-RESID-POST-AA
    11. 51623
    Prev
    Next
    INDEX
    Explanations

    вред

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.08
     sacrificed
    -0.08
    iquement
    -0.08
    retched
    -0.08
    tered
    -0.08
     forcibly
    -0.08
    ulated
    -0.07
    áte
    -0.07
    借
    -0.07
     হত
    -0.07
    POSITIVE LOGITS
    ителей
    0.10
    ителями
    0.10
     verursacht
    0.09
     нанос
    0.09
    ители
    0.09
    о
    0.09
    ակար
    0.09
    ительства
    0.09
    ونکو
    0.08
    ителя
    0.08
    Activations Density 0.001%

    No Known Activations