© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102884
    Prev
    Next
    INDEX
    Explanations

    Library inventory/database

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nipple
    -0.10
     wave
    -0.09
     awọ
    -0.09
     waveform
    -0.09
    entropy
    -0.09
     matlab
    -0.09
     Matlab
    -0.08
    _wave
    -0.08
    assim
    -0.08
     facelift
    -0.08
    POSITIVE LOGITS
     Book
    0.17
     inventory
    0.16
     CRUD
    0.16
     Employees
    0.16
    _books
    0.16
     Blog
    0.16
     books
    0.16
    Inventory
    0.16
     bookstore
    0.16
    Blog
    0.16
    Activations Density 0.017%

    No Known Activations