© 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. 18386
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ly
    -0.08
     байх
    -0.08
     باللغة
    -0.08
     पर्ने
    -0.08
     الطبي
    -0.08
     بسي
    -0.08
    ýsing
    -0.07
     كيفية
    -0.07
     طريقة
    -0.07
     على
    -0.07
    POSITIVE LOGITS
     already
    0.45
    already
    0.45
     Already
    0.43
    已经
    0.43
     bereits
    0.42
    Already
    0.41
     allerede
    0.40
     we've
    0.40
     уже
    0.39
     ఇప్పటికే
    0.38
    Activations Density 0.135%

    No Known Activations