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. 77234
    Prev
    Next
    INDEX
    Explanations

    1

    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
    져
    -0.08
    .acc
    -0.08
    党的
    -0.08
    cznej
    -0.07
    .partial
    -0.07
     itr
    -0.07
    早
    -0.07
    breviation
    -0.07
    atisfaction
    -0.07
    しま
    -0.07
    POSITIVE LOGITS
     Через
    0.09
     Худ
    0.08
     Ар
    0.08
     producteurs
    0.08
     Луч
    0.08
     podrán
    0.08
    VO
    0.08
     Ру
    0.07
     stared
    0.07
     hook
    0.07
    Activations Density 0.002%

    No Known Activations