© 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. 12962
    Prev
    Next
    INDEX
    Explanations

    与

    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
     fick
    -0.08
     typically
    -0.08
     Zak
    -0.08
     flats
    -0.08
     ruled
    -0.08
     seg
    -0.08
    উ
    -0.07
     Flats
    -0.07
     velo
    -0.07
     gotta
    -0.07
    POSITIVE LOGITS
     nhau
    0.10
     sheath
    0.08
     Doll
    0.07
    ינו
    0.07
     skipper
    0.07
    Mr
    0.07
    ceries
    0.07
     Mr
    0.07
    利益
    0.07
    ણી
    0.07
    Activations Density 0.032%

    No Known Activations