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. 43888
    Prev
    Next
    INDEX
    Explanations

    Japanese traditions involving "way"

    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
    ถูก
    -0.08
     pât
    -0.08
     tackled
    -0.08
    übers
    -0.07
     breakthrough
    -0.07
     tackle
    -0.07
    *self
    -0.07
    ****↵↵
    -0.07
    代表
    -0.07
    lüssel
    -0.07
    POSITIVE LOGITS
    習
    0.09
     voie
    0.08
     hábitos
    0.08
    унун
    0.08
     nzira
    0.08
     siga
    0.08
     siguen
    0.08
     Bowman
    0.08
     caminos
    0.08
     Practitioner
    0.08
    Activations Density 0.013%

    No Known Activations