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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 111663
    Prev
    Next
    INDEX
    Explanations

    name/title

    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
     planta
    -0.08
     bridging
    -0.08
     quorum
    -0.07
    param
    -0.07
    @Autowired
    -0.07
     parameter
    -0.07
     подобных
    -0.07
    [param
    -0.07
     zoeken
    -0.06
    شارك
    -0.06
    POSITIVE LOGITS
    名称
    0.11
     название
    0.10
     이름
    0.09
     name
    0.09
    /name
    0.09
     nazw
    0.09
     nama
    0.09
     નામ
    0.09
    名字
    0.09
    .Name
    0.09
    Activations Density 0.039%

    No Known Activations