© 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. 24641
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    次数
    -0.09
     ain
    -0.08
     änd
    -0.08
     Wholesale
    -0.08
    ाधिकारी
    -0.08
    ौं
    -0.08
    ां
    -0.07
     जब
    -0.07
    याँ
    -0.07
    Cos
    -0.07
    POSITIVE LOGITS
    รวม
    0.09
     способ
    0.08
     προσωπ
    0.08
     συλλ
    0.08
     понят
    0.07
    _pub
    0.07
     смысл
    0.07
     ġ
    0.07
     cov
    0.07
     STF
    0.07
    Activations Density 0.065%

    No Known Activations