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. 3-RESID-POST-AA
    6. 12241
    Prev
    Next
    INDEX
    Explanations

    Al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.09
     Dunk
    -0.08
     Solo
    -0.08
    留
    -0.08
     umi
    -0.08
    -0.08
     naka
    -0.08
    ugl
    -0.07
     Coat
    -0.07
    和平
    -0.07
    POSITIVE LOGITS
    693
    0.08
    conten
    0.08
     technique
    0.08
    βαι
    0.08
    Ws
    0.08
     idé
    0.07
    nw
    0.07
    FS
    0.07
    FI
    0.07
    whel
    0.07
    Activations Density 0.020%

    No Known Activations