Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 60946
    Prev
    Next
    INDEX
    Explanations

    shag

    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
     rigu
    -0.09
     Burkina
    -0.08
    体系
    -0.08
     ufa
    -0.08
     এট
    -0.08
     Cra
    -0.07
     Prec
    -0.07
     hành
    -0.07
    -Ass
    -0.07
     Cara
    -0.07
    POSITIVE LOGITS
    壮
    0.09
     Pet
    0.08
    Pet
    0.08
     Bonnie
    0.08
    itie
    0.07
    HH
    0.07
     rope
    0.07
    ening
    0.07
    hh
    0.07
     plur
    0.07
    Activations Density 0.001%

    No Known Activations