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. 54420
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     etabl
    -0.07
     detectable
    -0.07
     rekon
    -0.07
     beobachten
    -0.07
    .est
    -0.07
    μβ
    -0.07
     DEFINE
    -0.07
    _pm
    -0.07
    станавли
    -0.07
     এমন
    -0.07
    POSITIVE LOGITS
     toevoeg
    0.08
     acrescent
    0.08
     ઉમ
    0.08
     əlavə
    0.08
    ضاف
    0.08
    시면
    0.08
     adds
    0.08
     añadir
    0.08
     சேர
    0.08
     ajouté
    0.08
    Activations Density 0.028%

    No Known Activations