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. 44247
    Prev
    Next
    INDEX
    Explanations

    recycling

    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
     avr
    -0.08
    gl
    -0.07
     aquela
    -0.07
     glitch
    -0.07
     selfies
    -0.07
    (Method
    -0.07
    'assurer
    -0.07
     aquella
    -0.07
     quella
    -0.07
    Gl
    -0.07
    POSITIVE LOGITS
     recyclable
    0.09
     recycl
    0.08
     parada
    0.08
     recic
    0.08
     ماد
    0.08
     recicl
    0.08
    Backing
    0.08
     debido
    0.08
    cona
    0.07
     voordelen
    0.07
    Activations Density 0.004%

    No Known Activations