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. 67525
    Prev
    Next
    INDEX
    Explanations

    AD

    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
     Devil
    -0.09
     Churchill
    -0.08
     степени
    -0.08
     دام
    -0.08
    DISC
    -0.08
     року
    -0.08
    Chel
    -0.08
    Cep
    -0.08
     степень
    -0.08
    Temper
    -0.08
    POSITIVE LOGITS
     adip
    0.09
    ubo
    0.09
     pose
    0.07
     ménage
    0.07
     recipient
    0.07
     receiver
    0.07
     fasting
    0.07
    _pose
    0.07
     meal
    0.07
     wed
    0.07
    Activations Density 0.001%

    No Known Activations