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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29647
    Prev
    Next
    INDEX
    Explanations

    Middle Eastern dips

    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
     stochastic
    -0.09
     पीछ
    -0.08
     pursuing
    -0.08
    丈
    -0.08
     रहने
    -0.08
     covering
    -0.08
     predetermined
    -0.07
    >.
    -0.07
     executing
    -0.07
    .Visit
    -0.07
    POSITIVE LOGITS
     acara
    0.09
    undz
    0.09
    acamole
    0.08
     humm
    0.08
    ichannel
    0.08
     margar
    0.08
     Verk
    0.08
     blends
    0.08
    ündet
    0.08
     naut
    0.08
    Activations Density 0.005%

    No Known Activations