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. 98622
    Prev
    Next
    INDEX
    Explanations

    frac

    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
    )_
    -0.11
    ]_
    -0.11
    }_
    -0.10
    )^
    -0.10
    '_
    -0.09
    -अलग
    -0.09
    ーフ
    -0.08
     beoordelingen
    -0.08
     "__
    -0.08
    <|reserved_200004|>
    -0.08
    POSITIVE LOGITS
     {{
    0.17
     {(
    0.17
     {
    0.16
    23
    0.15
    14
    0.14
    34
    0.14
    13
    0.14
     {|
    0.13
    35
    0.13
    15
    0.13
    Activations Density 0.042%

    No Known Activations