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. 46360
    Prev
    Next
    INDEX
    Explanations

    sub

    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
     therapy
    -0.08
     терапии
    -0.08
     treatment
    -0.08
     ചികിത്സ
    -0.08
     gathered
    -0.08
     topic
    -0.08
    (topic
    -0.08
     വിഷയ
    -0.07
    ={`${
    -0.07
    Merge
    -0.07
    POSITIVE LOGITS
    _AG
    0.08
    Tas
    0.08
     daarvan
    0.08
    aiser
    0.08
     hz
    0.08
     boasting
    0.08
     cautious
    0.08
     kilometer
    0.07
     Tas
    0.07
    خرى
    0.07
    Activations Density 0.005%

    No Known Activations