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. 27258
    Prev
    Next
    INDEX
    Explanations

    Dialectical behavior therapy

    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
     tassa
    -0.10
    berger
    -0.09
     verhe
    -0.08
    Variant
    -0.08
     النبات
    -0.08
    Hide
    -0.08
    柴油
    -0.08
    Overwrite
    -0.08
    .hide
    -0.08
     installeren
    -0.08
    POSITIVE LOGITS
    utils
    0.09
     विवाद
    0.08
     esforços
    0.08
     scandals
    0.08
    !!
    0.08
     disputes
    0.08
     skills
    0.07
    争
    0.07
     emergencies
    0.07
    okwadi
    0.07
    Activations Density 0.002%

    No Known Activations