© 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. 79512
    Prev
    Next
    INDEX
    Explanations

    direct explicit

    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
     absol
    -0.08
     입
    -0.08
     होता
    -0.08
     있다는
    -0.08
     Miracle
    -0.08
     Swiss
    -0.07
    aisse
    -0.07
    _hresult
    -0.07
     सुपर
    -0.07
    idus
    -0.07
    POSITIVE LOGITS
     maupun
    0.13
    explicit
    0.09
     емес
    0.09
     threats
    0.08
     ataupun
    0.08
     эмес
    0.08
     explicit
    0.08
    ない
    0.08
     tế
    0.08
     וגם
    0.08
    Activations Density 0.046%

    No Known Activations