© 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. 50550
    Prev
    Next
    INDEX
    Explanations

    below a limit

    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
     suure
    -0.11
     bigger
    -0.11
     höhere
    -0.11
     grotere
    -0.11
     größere
    -0.11
     larger
    -0.11
     hogere
    -0.10
     groter
    -0.10
     taller
    -0.10
     größer
    -0.10
    POSITIVE LOGITS
    below
    0.19
     below
    0.19
     abaixo
    0.18
     stays
    0.18
     Below
    0.17
     staying
    0.17
     Stay
    0.17
     acceptable
    0.17
     stay
    0.17
    Below
    0.17
    Activations Density 0.071%

    No Known Activations