© 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. 3-RESID-POST-AA
    11. 1415
    Prev
    Next
    INDEX
    Explanations

    wave

    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
     definitions
    -0.08
     enlightened
    -0.08
     apoptosis
    -0.08
     episodes
    -0.07
     ആറ
    -0.07
     episode
    -0.07
     institutions
    -0.07
     Episodes
    -0.07
    рой
    -0.07
     Episode
    -0.07
    POSITIVE LOGITS
     যোগাযোগ
    0.09
     emiss
    0.08
    żu
    0.08
     ప్రస
    0.08
     송
    0.08
     передачи
    0.08
    通信
    0.08
     acrylic
    0.08
     Sun
    0.08
    .header
    0.08
    Activations Density 0.015%

    No Known Activations