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. 98293
    Prev
    Next
    INDEX
    Explanations

    backslash

    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
    》和
    -0.12
     மற்றும்
    -0.10
     和
    -0.09
    ,and
    -0.09
    和
    -0.09
     және
    -0.09
    ýs
    -0.09
     અને
    -0.09
     and
    -0.09
     এবং
    -0.09
    POSITIVE LOGITS
    quad
    0.13
    qqu
    0.10
     
    0.09
    ;↵
    0.08
     quad
    0.08
    ~~
    0.08
    ;
    ↵
    0.08
     adapters
    0.08
    ;\↵
    0.08
    धे
    0.08
    Activations Density 0.013%

    No Known Activations