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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18541
    Prev
    Next
    INDEX
    Explanations

    already

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.08
    ity
    -0.08
    ിലൂടെ
    -0.07
    לה
    -0.07
    BUT
    -0.07
    ాలి
    -0.07
    ാക്
    -0.07
     사항
    -0.07
    ികൾ
    -0.07
    ുവ
    -0.06
    POSITIVE LOGITS
     already
    0.63
    already
    0.58
     Already
    0.55
     allerede
    0.54
    Already
    0.54
     bereits
    0.53
     уже
    0.52
     ఇప్పటికే
    0.51
     ήδη
    0.51
     redan
    0.50
    Activations Density 0.274%

    No Known Activations