Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12893
    Prev
    Next
    INDEX
    Explanations

    code/GPT agents/URLs

    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
     Schluss
    -0.08
     yada
    -0.08
    ’ay
    -0.07
    üt
    -0.07
    orch
    -0.07
    .Generate
    -0.07
    öffnung
    -0.07
     suburban
    -0.07
    وجل
    -0.07
     suburbs
    -0.07
    POSITIVE LOGITS
     traduit
    0.08
     vietnam
    0.08
     sellest
    0.08
     copia
    0.08
     клад
    0.08
     jeunesse
    0.08
     trad
    0.08
     traduction
    0.08
     serais
    0.08
     techno
    0.07
    Activations Density 0.000%

    No Known Activations