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. 102941
    Prev
    Next
    INDEX
    Explanations

    .lower

    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
     Authority
    -0.09
     authority
    -0.09
     രാഷ്ട്രീയ
    -0.08
     ofert
    -0.08
     రాజకీయ
    -0.07
     Countries
    -0.07
     राजनीति
    -0.07
     Nations
    -0.07
     mouths
    -0.07
    ERT
    -0.07
    POSITIVE LOGITS
    _yes
    0.09
    breviation
    0.09
    _terminal
    0.09
     раств
    0.09
     morgens
    0.09
    terminal
    0.09
    cres
    0.08
    轻
    0.08
    abbr
    0.08
    fast
    0.08
    Activations Density 0.002%

    No Known Activations