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. 131037
    Prev
    Next
    INDEX
    Explanations

    breeding

    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
     Lyc
    -0.08
     mish
    -0.07
    ded
    -0.07
    _ESCAPE
    -0.07
    once
    -0.07
    _Sub
    -0.07
     seri
    -0.06
     notif
    -0.06
     apparition
    -0.06
     Abenteuer
    -0.06
    POSITIVE LOGITS
     proverbial
    0.12
    -yard
    0.12
     valve
    0.11
     room
    0.11
     valves
    0.11
    -sheet
    0.11
    -room
    0.10
     ride
    0.10
    -ticket
    0.10
    _room
    0.10
    Activations Density 0.174%

    No Known Activations