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. 58843
    Prev
    Next
    INDEX
    Explanations

    concern

    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
    achine
    -0.08
     வக
    -0.08
    él
    -0.08
     தெ
    -0.08
     чет
    -0.08
    emm
    -0.07
     класса
    -0.07
     கடந்த
    -0.07
     கட
    -0.07
    éb
    -0.07
    POSITIVE LOGITS
     mare
    0.09
    患
    0.08
     secours
    0.08
    .Println
    0.08
    Coverage
    0.08
     immensely
    0.08
     prognosis
    0.08
     symptoms
    0.08
    دای
    0.07
     injuries
    0.07
    Activations Density 0.011%

    No Known Activations