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. 130757
    Prev
    Next
    INDEX
    Explanations

    just

    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
     continuará
    -0.09
     präsentiert
    -0.09
     präsentieren
    -0.09
    .deepcopy
    -0.08
    .Unmarshal
    -0.08
     präsent
    -0.08
     অসম
    -0.08
    orton
    -0.08
     обеспеч
    -0.08
     aiding
    -0.08
    POSITIVE LOGITS
     let
    0.35
    Let
    0.28
     Let
    0.28
    	let
    0.27
    let
    0.24
     letting
    0.24
    (let
    0.22
     Laat
    0.21
     laat
    0.20
     lets
    0.19
    Activations Density 0.022%

    No Known Activations