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. 130090
    Prev
    Next
    INDEX
    Explanations

    like

    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
     ging
    -0.10
    .up
    -0.09
    .rate
    -0.08
    .respond
    -0.08
     washable
    -0.08
    %;">↵
    -0.08
     obn
    -0.08
    .processor
    -0.08
    וכל
    -0.08
    ายน
    -0.08
    POSITIVE LOGITS
     firsthand
    0.13
     hardships
    0.12
     અનુભવ
    0.12
     experience
    0.11
     realities
    0.11
    体验
    0.11
     hardship
    0.11
     experiences
    0.10
    経験
    0.10
    苦
    0.10
    Activations Density 0.114%

    No Known Activations