Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2275
    Prev
    Next
    INDEX
    Explanations

    is

    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
     tanks
    -0.08
    ข้อความ
    -0.08
     dirt
    -0.07
     anon
    -0.07
     pembangunan
    -0.07
     ambulance
    -0.07
    onges
    -0.07
     ус
    -0.07
    зіць
    -0.07
     TLS
    -0.07
    POSITIVE LOGITS
    Fan
    0.08
    Dd
    0.08
     Mandel
    0.08
    Op
    0.07
     Lawson
    0.07
     Sonia
    0.07
     Shah
    0.07
    Ae
    0.07
    27
    0.07
    300
    0.07
    Activations Density 0.060%

    No Known Activations