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. 49333
    Prev
    Next
    INDEX
    Explanations

    game development code

    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
     Humanities
    -0.08
    .unsubscribe
    -0.07
     Mailing
    -0.07
     reacting
    -0.07
     plas
    -0.07
     Ballroom
    -0.07
     Bahn
    -0.07
    -0.07
    Ether
    -0.07
    dsl
    -0.07
    POSITIVE LOGITS
     إص
    0.09
     accommod
    0.08
    .ht
    0.08
     robber
    0.08
    agment
    0.08
    Adjustment
    0.08
     aposent
    0.07
    igua
    0.07
    imburse
    0.07
    Argb
    0.07
    Activations Density 0.001%

    No Known Activations