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. 12082
    Prev
    Next
    INDEX
    Explanations

    world, practical

    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
     الرد
    -0.08
     Recl
    -0.08
     NRC
    -0.08
     Ruiz
    -0.08
     untreated
    -0.08
    (Card
    -0.08
     Mün
    -0.08
     futile
    -0.07
    (Z
    -0.07
    _z
    -0.07
    POSITIVE LOGITS
     경험
    0.10
     실제
    0.10
     અનુભવ
    0.10
     experience
    0.10
     અનુભ
    0.09
     ervaring
    0.09
     expérience
    0.09
     prag
    0.09
     realism
    0.09
     industrial
    0.09
    Activations Density 0.024%

    No Known Activations