© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 79090
    Prev
    Next
    INDEX
    Explanations

    is

    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
     structures
    -0.08
     sin
    -0.08
     capas
    -0.07
     texture
    -0.07
     instant
    -0.07
     agregar
    -0.07
     distorted
    -0.07
     sediment
    -0.07
     distortion
    -0.07
     horizonte
    -0.07
    POSITIVE LOGITS
    хь
    0.09
     unexpectedly
    0.09
     mysterious
    0.09
     voluntarily
    0.09
     راغ
    0.08
    рыем
    0.08
     ellipse
    0.08
    чыма
    0.08
    ellipse
    0.08
     మాత్ర
    0.08
    Activations Density 0.017%

    No Known Activations