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. 43105
    Prev
    Next
    INDEX
    Explanations

    biological processes

    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
    ੈ
    -0.08
     parliamentary
    -0.08
     rows
    -0.08
     Netflix
    -0.08
    rows
    -0.08
    par
    -0.07
    .MEDIA
    -0.07
     Aleks
    -0.07
     filas
    -0.07
     paranormal
    -0.07
    POSITIVE LOGITS
    Initialize
    0.10
     تجهيز
    0.09
    ،↵
    0.09
     laminated
    0.09
    verify
    0.09
    etooth
    0.09
    'activ
    0.09
     bicycle
    0.08
    Verify
    0.08
     تأ
    0.08
    Activations Density 0.002%

    No Known Activations