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. 30654
    Prev
    Next
    INDEX
    Explanations

    IN

    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
    NL
    -0.08
     Lift
    -0.07
     Apart
    -0.07
    809
    -0.07
     Zwe
    -0.07
    (cls
    -0.07
    890
    -0.07
    зь
    -0.07
     ಜೊ
    -0.07
     instrument
    -0.07
    POSITIVE LOGITS
    -Sm
    0.09
     grat
    0.09
    iters
    0.08
     fung
    0.08
    Payment
    0.08
    онач
    0.08
    Greetings
    0.08
     worthless
    0.08
    Winning
    0.08
    wetten
    0.08
    Activations Density 0.001%

    No Known Activations