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. 106156
    Prev
    Next
    INDEX
    Explanations

    phases and durations

    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
     giant
    -0.09
     Eisen
    -0.08
     중요한
    -0.07
    ાનો
    -0.07
     erro
    -0.07
    ાના
    -0.07
    (VAR
    -0.07
    	LOGGER
    -0.07
     écologique
    -0.07
     orbit
    -0.07
    POSITIVE LOGITS
    'environ
    0.09
    .um
    0.08
    03
    0.08
    是多少
    0.08
     potrzeb
    0.08
     Вс
    0.07
     বছর
    0.07
     আন
    0.07
     Aeros
    0.07
     تقريب
    0.07
    Activations Density 0.022%

    No Known Activations