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. 27422
    Prev
    Next
    INDEX
    Explanations

    document

    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
    ට
    -0.09
     bağ
    -0.08
    یشه
    -0.08
     мужчины
    -0.08
     ziehen
    -0.08
    iczne
    -0.08
     Appointment
    -0.08
     Suffolk
    -0.08
    ින්
    -0.08
    ක්
    -0.08
    POSITIVE LOGITS
    .station
    0.08
    +'.
    0.08
                     
    0.07
     procédures
    0.07
                      
    0.07
    [layer
    0.07
                 
    0.07
                       
    0.07
    Station
    0.07
     veneer
    0.07
    Activations Density 0.004%

    No Known Activations