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. 11910
    Prev
    Next
    INDEX
    Explanations

    network classes

    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
    span
    -0.08
     tunn
    -0.07
    彩乐
    -0.07
     software
    -0.07
     tunne
    -0.07
     tunnels
    -0.07
    gaming
    -0.07
     chronological
    -0.07
     span
    -0.07
    _inc
    -0.07
    POSITIVE LOGITS
    (DEFAULT
    0.09
     oficio
    0.08
     বিভ
    0.08
     विभ
    0.08
     默认
    0.08
     negligent
    0.08
    -fashioned
    0.08
    DEFAULT
    0.08
    **/↵↵
    0.08
     */↵↵//
    0.08
    Activations Density 0.001%

    No Known Activations