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. 49573
    Prev
    Next
    INDEX
    Explanations

    mention

    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
     Examination
    -0.08
    ӯз
    -0.08
     Examine
    -0.08
    eros
    -0.08
     examination
    -0.07
    ење
    -0.07
    ám
    -0.07
     Evaluation
    -0.07
     Inspection
    -0.07
     sería
    -0.07
    POSITIVE LOGITS
     ausdrücklich
    0.09
    Messaging
    0.09
    Parts
    0.08
     ذكر
    0.08
     explicitly
    0.08
     পরে
    0.08
     immediately
    0.08
     сразу
    0.08
    明确
    0.08
    Likes
    0.08
    Activations Density 0.032%

    No Known Activations