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. 9070
    Prev
    Next
    INDEX
    Explanations

    :

    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
     aquarium
    -0.08
     canvi
    -0.08
     Bolt
    -0.08
    ække
    -0.07
     koste
    -0.07
     footh
    -0.07
     stake
    -0.07
    ρή
    -0.07
     lagere
    -0.07
     Wij
    -0.07
    POSITIVE LOGITS
    _href
    0.08
    日期
    0.07
     தேதி
    0.07
    ighters
    0.07
    ">(
    0.07
    _me
    0.07
    人与
    0.07
    undi
    0.07
    adv
    0.07
    roups
    0.07
    Activations Density 0.001%

    No Known Activations