© 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. 23-RESID-POST-AA
    11. 96304
    Prev
    Next
    INDEX
    Explanations

    sensory perceptions

    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
     considera
    -0.09
     considers
    -0.08
    ิจ
    -0.08
    иби
    -0.08
     considère
    -0.08
     hoppas
    -0.08
     berharap
    -0.07
     consideran
    -0.07
    시키
    -0.07
     considerar
    -0.07
    POSITIVE LOGITS
     looked
    0.16
     look
    0.16
     weighs
    0.15
     weigh
    0.14
     looks
    0.14
     weighed
    0.14
     smells
    0.14
     wygl
    0.14
     izgled
    0.13
     tastes
    0.13
    Activations Density 0.126%

    No Known Activations