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. 112103
    Prev
    Next
    INDEX
    Explanations

    ots

    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
     Prosper
    -0.08
     alph
    -0.07
     sifat
    -0.07
     datasource
    -0.07
     cosm
    -0.07
     structs
    -0.07
     같은
    -0.07
    )));↵↵
    -0.06
     Ash
    -0.06
    -0.06
    POSITIVE LOGITS
     irgende
    0.09
    mittlung
    0.08
    .ct
    0.08
     nhu
    0.08
     مدى
    0.08
     đo
    0.07
     juht
    0.07
     mikil
    0.07
     tæt
    0.07
     أجل
    0.07
    Activations Density 0.002%

    No Known Activations