© 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. 50629
    Prev
    Next
    INDEX
    Explanations

    Arabic/Indian intellectuals and math

    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
    _scalar
    -0.09
    كال
    -0.08
     דיס
    -0.08
    CEA
    -0.08
     EPL
    -0.08
     curved
    -0.08
     discriminator
    -0.08
    .uml
    -0.07
    Scalar
    -0.07
    .motor
    -0.07
    POSITIVE LOGITS
     hosting
    0.08
     tunn
    0.08
    hosting
    0.08
    *out
    0.07
     host
    0.07
    Hosting
    0.07
    น
    0.07
    Instances
    0.07
     user
    0.07
     instances
    0.07
    Activations Density 0.003%

    No Known Activations