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. 45212
    Prev
    Next
    INDEX
    Explanations

    SSD and memory management

    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
     companions
    -0.09
     compagnon
    -0.08
    compan
    -0.07
    'occ
    -0.07
     Poi
    -0.07
     profit
    -0.07
     profits
    -0.07
     warto
    -0.07
    abre
    -0.07
    iali
    -0.07
    POSITIVE LOGITS
    arani
    0.09
     ekki
    0.09
     individuele
    0.09
     selectable
    0.08
    auxite
    0.08
     delet
    0.08
     elector
    0.08
     uitger
    0.08
     bereid
    0.08
    annelse
    0.08
    Activations Density 0.001%

    No Known Activations