© 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. 7-RESID-POST-AA
    11. 1436
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     어느
    -0.08
     Heide
    -0.08
    ્યું
    -0.08
     Tou
    -0.08
     verp
    -0.08
     expon
    -0.08
     redesigned
    -0.08
     angepasst
    -0.08
     voie
    -0.08
    UY
    -0.07
    POSITIVE LOGITS
    rob
    0.08
    Rob
    0.08
    Interest
    0.07
     {\
    0.07
     Engel
    0.07
    0.07
    stood
    0.07
    onacci
    0.07
    Eligible
    0.07
     modest
    0.07
    Activations Density 0.017%
    No Known Activations