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. 7-RESID-POST-AA
    6. 1807
    Prev
    Next
    INDEX
    Explanations

    anodized aluminum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meng
    -0.08
     Cop
    -0.07
     Nexus
    -0.07
     znal
    -0.07
     jednost
    -0.07
     Česk
    -0.07
     wi
    -0.07
     nim
    -0.07
     Em
    -0.07
     Auto
    -0.07
    POSITIVE LOGITS
     gains
    0.08
     religi
    0.08
     Redskins
    0.08
    ENDED
    0.07
    oton
    0.07
     chemically
    0.07
     fiery
    0.07
     optar
    0.07
     ampli
    0.07
    optic
    0.07
    Activations Density 0.000%

    No Known Activations