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. 76126
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Zones
    -0.07
     CMS
    -0.07
     vols
    -0.07
     Big
    -0.07
     Crossing
    -0.07
     }):
    -0.07
     Zone
    -0.07
     cesse
    -0.07
     plastique
    -0.07
    going
    -0.07
    POSITIVE LOGITS
     unn
    0.09
    描
    0.08
     improbable
    0.08
     രംഗ
    0.08
     insinu
    0.08
     surrounding
    0.08
    _hint
    0.08
     සිට
    0.08
    nip
    0.08
    ...↵↵↵↵
    0.08
    Activations Density 0.007%

    No Known Activations