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. 119206
    Prev
    Next
    INDEX
    Explanations

    Database column names/IDs

    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
    Duck
    -0.08
    -0.08
    HP
    -0.08
    flies
    -0.08
     Abschluss
    -0.08
     irrational
    -0.07
    bounce
    -0.07
     absch
    -0.07
    து
    -0.07
    挣
    -0.07
    POSITIVE LOGITS
     എന്ന്
    0.08
     deres
    0.08
     എന്നും
    0.08
     ผู้
    0.08
     financing
    0.07
     정부
    0.07
     土
    0.07
    ET
    0.07
    remely
    0.07
     wɔ
    0.07
    Activations Density 0.012%

    No Known Activations