© 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. 3-RESID-POST-AA
    11. 12719
    Prev
    Next
    INDEX
    Explanations

    aşağı

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gleich
    -0.08
     ordained
    -0.07
    ;x
    -0.07
     Alexandra
    -0.07
    -u
    -0.07
     Sänger
    -0.07
     MAD
    -0.07
     Regen
    -0.07
    /apis
    -0.07
     cad
    -0.07
    POSITIVE LOGITS
     Bola
    0.08
    的话
    0.08
     refr
    0.07
    та
    0.07
     baie
    0.07
     prett
    0.07
    Comparator
    0.07
    Swap
    0.07
    eke
    0.07
    colors
    0.07
    Activations Density 0.000%

    No Known Activations