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. 88066
    Prev
    Next
    INDEX
    Explanations

    image/video fine detail

    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
     charging
    -0.10
    charging
    -0.09
     Charging
    -0.09
     Gilles
    -0.08
     itin
    -0.08
    Charging
    -0.08
     megh
    -0.08
     durations
    -0.08
     batteries
    -0.08
     rechargeable
    -0.08
    POSITIVE LOGITS
     pixel
    0.12
    _pixel
    0.12
     Pixel
    0.12
    pixel
    0.12
     વિગતો
    0.12
     деталей
    0.12
    纹
    0.11
     детали
    0.11
     JPEG
    0.11
    Pixel
    0.11
    Activations Density 0.013%

    No Known Activations