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. 3-RESID-POST-AA
    6. 2131
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alloy
    -0.07
    crow
    -0.07
     Seed
    -0.07
     pihak
    -0.07
     crowd
    -0.07
     graft
    -0.07
     lop
    -0.07
     Preg
    -0.07
     league
    -0.07
     residency
    -0.07
    POSITIVE LOGITS
     علامات
    0.08
     justificar
    0.08
     Antar
    0.08
    μός
    0.08
     OBS
    0.08
    手机下载
    0.08
     alternatively
    0.07
    antar
    0.07
    ательства
    0.07
    óf
    0.07
    Activations Density 0.000%

    No Known Activations