Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60907
    Prev
    Next
    INDEX
    Explanations

    tqdm

    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
     Baltimore
    -0.08
    Verification
    -0.08
    CARE
    -0.08
    դրբեջ
    -0.08
    ölker
    -0.08
    .Measure
    -0.08
    .Skill
    -0.08
    .CASCADE
    -0.08
    .City
    -0.08
    Schedules
    -0.08
    POSITIVE LOGITS
     stirred
    0.07
     chew
    0.07
    tow
    0.07
    tre
    0.07
    ten
    0.07
     Heading
    0.07
     besonderen
    0.07
    nya
    0.07
    title
    0.07
     Сам
    0.07
    Activations Density 0.000%

    No Known Activations