© 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. 110410
    Prev
    Next
    INDEX
    Explanations

    tautologies

    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
     ulike
    -0.08
     Jeg
    -0.08
    不同
    -0.08
     विभिन्न
    -0.07
     različ
    -0.07
     ^↵
    -0.07
     różnych
    -0.07
     Edge
    -0.07
     grøn
    -0.07
    ando
    -0.07
    POSITIVE LOGITS
     worthless
    0.12
     useless
    0.10
     trivial
    0.10
     meaningless
    0.10
     hardly
    0.10
     taut
    0.10
     pointless
    0.09
     unnecessarily
    0.09
     silly
    0.08
    essential
    0.08
    Activations Density 0.025%

    No Known Activations