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. 65123
    Prev
    Next
    INDEX
    Explanations

    probabilities

    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
    otl
    -0.10
     layouts
    -0.09
    קת
    -0.08
     nọ
    -0.08
    범
    -0.08
     Preview
    -0.08
    (Layout
    -0.08
    ային
    -0.08
     Layout
    -0.08
     dédié
    -0.08
    POSITIVE LOGITS
     surviv
    0.13
     survival
    0.13
     surviving
    0.12
     Survival
    0.12
     lifespan
    0.11
     survives
    0.11
     survived
    0.11
     జీవిత
    0.11
     survive
    0.10
     superviv
    0.10
    Activations Density 0.005%

    No Known Activations