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. 9056
    Prev
    Next
    INDEX
    Explanations

    audience

    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
    osis
    -0.08
    atic
    -0.08
     inflicted
    -0.08
     активности
    -0.08
    .can
    -0.08
    ritic
    -0.08
    נע
    -0.07
    .ful
    -0.07
     denunc
    -0.07
     борьбы
    -0.07
    POSITIVE LOGITS
     audiences
    0.18
     audience
    0.18
    Audience
    0.17
     ప్రేక్షక
    0.16
     Audience
    0.15
     جمهور
    0.14
     الجمهور
    0.14
     аудит
    0.13
     readership
    0.13
     audiencia
    0.12
    Activations Density 0.041%

    No Known Activations