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. 87951
    Prev
    Next
    INDEX
    Explanations

    calculations

    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
    -Kom
    -0.09
     kom
    -0.08
     pě
    -0.08
     તેમના
    -0.08
    veck
    -0.08
     ઉત
    -0.08
    ningar
    -0.08
     yöntem
    -0.08
     Create
    -0.08
     shy
    -0.07
    POSITIVE LOGITS
    Roboto
    0.10
     beneficial
    0.09
    ALLY
    0.09
    .LOGIN
    0.08
     thata
    0.08
     RAND
    0.08
    KT
    0.08
     built
    0.07
     económ
    0.07
    Built
    0.07
    Activations Density 0.069%

    No Known Activations