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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44380
    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
     zunächst
    -0.08
    (ab
    -0.08
     лидер
    -0.08
     dubbed
    -0.07
    _ann
    -0.07
     занятия
    -0.07
     хут
    -0.07
     淘
    -0.07
     towing
    -0.07
    弹
    -0.07
    POSITIVE LOGITS
     culminating
    0.08
     BIS
    0.08
     حتى
    0.08
     akhirnya
    0.08
     blah
    0.08
    nable
    0.08
     DEALINGS
    0.07
     TABLE
    0.07
     billions
    0.07
    iyas
    0.07
    Activations Density 0.029%

    No Known Activations