© 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. 110857
    Prev
    Next
    INDEX
    Explanations

    radius

    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
    objs
    -0.09
     objects
    -0.09
    都有
    -0.08
     muebles
    -0.08
     delivered
    -0.08
    .Annotation
    -0.07
     terasa
    -0.07
     ना
    -0.07
     archivos
    -0.07
     objetos
    -0.07
    POSITIVE LOGITS
    -radius
    0.10
     raiz
    0.08
    (radius
    0.08
    _radius
    0.08
    ,result
    0.08
     sqrt
    0.08
    明星
    0.08
     radius
    0.08
    েড
    0.08
    Ryan
    0.08
    Activations Density 0.009%

    No Known Activations