© 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. 3-RESID-POST-AA
    11. 13100
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ese
    -0.08
     Pillow
    -0.08
     Teddy
    -0.08
     poud
    -0.08
     ভয়
    -0.07
     cumpleaños
    -0.07
    -0.07
     Pens
    -0.07
    াথ
    -0.07
     skoraj
    -0.07
    POSITIVE LOGITS
    'ins
    0.07
    funnels
    0.07
    bum
    0.07
    Ins
    0.07
    Incl
    0.07
     වි
    0.07
    mouth
    0.07
    404
    0.07
    .Variable
    0.07
     judgment
    0.07
    Activations Density 0.000%
    No Known Activations