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. 45144
    Prev
    Next
    INDEX
    Explanations

    commas and bold markers

    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
    游客
    -0.09
    Spi
    -0.09
    破解
    -0.09
     certificados
    -0.08
     seizures
    -0.08
    EAN
    -0.08
     pierres
    -0.08
    Otp
    -0.08
    ICP
    -0.08
     وتق
    -0.08
    POSITIVE LOGITS
     colleague
    0.12
     teammate
    0.11
     coworkers
    0.11
     cowork
    0.11
     Kollegen
    0.10
     업무
    0.10
     Employee
    0.10
     colleagues
    0.10
     collègues
    0.10
    shortcut
    0.10
    Activations Density 0.018%

    No Known Activations