© 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. 95010
    Prev
    Next
    INDEX
    Explanations

    fake/fictional

    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
     Browns
    -0.07
     prized
    -0.07
     Martínez
    -0.07
     представить
    -0.07
     도
    -0.06
     Martinez
    -0.06
    _shared
    -0.06
     الحديث
    -0.06
    િંગ
    -0.06
    利
    -0.06
    POSITIVE LOGITS
     mythical
    0.09
     Fake
    0.08
    ాచ్
    0.08
    -but
    0.08
     LINK
    0.08
    >x
    0.08
     üst
    0.08
     tack
    0.08
    _te
    0.08
     Lyft
    0.08
    Activations Density 0.007%

    No Known Activations