© 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. 1332
    Prev
    Next
    INDEX
    Explanations

    timely

    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
     beurte
    -0.09
    �
    -0.07
    som
    -0.07
     wagen
    -0.07
     eff
    -0.07
     ij
    -0.07
     evaluated
    -0.07
     Will
    -0.07
     التك
    -0.07
    辨
    -0.06
    POSITIVE LOGITS
     nitr
    0.08
    Corr
    0.08
     terk
    0.08
     Citr
    0.08
     Cru
    0.08
     अनुप
    0.08
    Ut
    0.07
     Umb
    0.07
    Tes
    0.07
    _tmp
    0.07
    Activations Density 0.004%

    No Known Activations