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. 42115
    Prev
    Next
    INDEX
    Explanations

    many

    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
    قية
    -0.08
     certain
    -0.08
    Repeated
    -0.08
    ("../../
    -0.07
     urč
    -0.07
    KIT
    -0.07
    Certain
    -0.07
    Spaces
    -0.07
    cation
    -0.07
    quat
    -0.07
    POSITIVE LOGITS
     vastly
    0.10
     depending
    0.09
    ので
    0.09
     myriad
    0.09
     Depending
    0.09
    -ranging
    0.09
     dozens
    0.08
    ,因此
    0.08
     разнообраз
    0.08
     зависит
    0.08
    Activations Density 0.057%

    No Known Activations