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. 117558
    Prev
    Next
    INDEX
    Explanations

    Permissions and safety

    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
    จังหวัด
    -0.08
    prung
    -0.08
    ,None
    -0.07
    =None
    -0.07
    appropr
    -0.07
    ,row
    -0.07
    edded
    -0.07
    움을
    -0.07
     convention
    -0.07
     geschreven
    -0.07
    POSITIVE LOGITS
     limitée
    0.11
     Allowed
    0.11
    限制
    0.11
     সীম
    0.11
    _LIMIT
    0.11
     forbid
    0.11
     erlaub
    0.11
     allowed
    0.10
    allowed
    0.10
     limitar
    0.10
    Activations Density 0.004%

    No Known Activations