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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 131033
    Prev
    Next
    INDEX
    Explanations

    Br

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Since
    -0.08
     Since
    -0.08
     Frederik
    -0.08
     وسلم
    -0.07
     since
    -0.07
     totalement
    -0.07
    _DIST
    -0.07
    ాప్తంగా
    -0.07
    //=
    -0.07
     completely
    -0.07
    POSITIVE LOGITS
    igitte
    0.20
    isbane
    0.15
    asserie
    0.15
    illiance
    0.15
    unswick
    0.14
    unei
    0.14
    ussels
    0.14
    ackets
    0.14
    andenburg
    0.13
    acket
    0.13
    Activations Density 0.027%

    No Known Activations