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. 78538
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
    皆
    -0.07
     tempered
    -0.07
     crystall
    -0.07
     terraces
    -0.07
    家
    -0.07
    ుంది
    -0.07
     blockchain
    -0.07
     Griffith
    -0.07
     மெ
    -0.07
     relentless
    -0.07
    POSITIVE LOGITS
     بنانے
    0.09
     brauch
    0.08
    epend
    0.08
     বাত
    0.08
     Jenna
    0.08
     Valentino
    0.08
     beauties
    0.07
     dyes
    0.07
     aet
    0.07
    letje
    0.07
    Activations Density 0.002%

    No Known Activations