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. 11-RESID-POST-AA
    6. 74593
    Prev
    Next
    INDEX
    Explanations

    photography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     COO
    -0.08
    skrä
    -0.08
     multas
    -0.08
     महस
    -0.08
     obstacle
    -0.08
    Obstacle
    -0.08
     akar
    -0.08
     Kepala
    -0.07
     Earnings
    -0.07
     CWE
    -0.07
    POSITIVE LOGITS
     photography
    0.11
    摄影
    0.11
     vintage
    0.11
     shutter
    0.10
    纸
    0.10
     photographie
    0.10
     photographic
    0.10
     fotografía
    0.10
     microscopy
    0.10
    自拍
    0.10
    Activations Density 0.017%

    No Known Activations