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. 98185
    Prev
    Next
    INDEX
    Explanations

    dem

    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
    escence
    -0.09
     Lus
    -0.09
    entation
    -0.09
     lanzamiento
    -0.08
    endamento
    -0.08
    (Current
    -0.08
     lanz
    -0.08
     renovation
    -0.08
     renovación
    -0.08
    letic
    -0.08
    POSITIVE LOGITS
    yst
    0.14
    ocrat
    0.11
    utes
    0.11
    oral
    0.10
    YST
    0.10
    ocr
    0.09
    UTES
    0.09
    otes
    0.08
    aterial
    0.08
    ysters
    0.08
    Activations Density 0.001%

    No Known Activations