Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 52965
    Prev
    Next
    INDEX
    Explanations

    code timers

    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
     �
    -0.10
     Finals
    -0.10
     halftime
    -0.09
     streng
    -0.09
     violated
    -0.09
    ¾
    -0.08
     :.
    -0.08
    apult
    -0.08
     �
    -0.08
     تب
    -0.08
    POSITIVE LOGITS
    Karl
    0.08
    agir
    0.08
    Modulo
    0.08
    Signal
    0.07
    માન
    0.07
    Sistema
    0.07
    react
    0.07
    ದಿ
    0.07
    Sit
    0.07
    Servico
    0.07
    Activations Density 0.000%

    No Known Activations