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. 53184
    Prev
    Next
    INDEX
    Explanations

    Vector algebra

    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
     wording
    -0.08
    807
    -0.08
     vuelva
    -0.07
     Municipal
    -0.07
     promin
    -0.07
     Mum
    -0.07
     PL
    -0.07
    PL
    -0.07
     possible
    -0.07
     Perf
    -0.07
    POSITIVE LOGITS
    Answers
    0.08
     тұ
    0.08
    .codes
    0.08
    Jan
    0.07
    undir
    0.07
    λών
    0.07
    Dé
    0.07
     dés
    0.07
     drog
    0.07
    .v
    0.07
    Activations Density 0.068%

    No Known Activations