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. 106222
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     symptoms
    -0.09
     Symptoms
    -0.09
    maßnahmen
    -0.08
    clipboard
    -0.08
    technology
    -0.07
    jö
    -0.07
    (scope
    -0.07
    analytics
    -0.07
     hardworking
    -0.07
    amples
    -0.07
    POSITIVE LOGITS
     decomposition
    0.09
     decom
    0.09
     dostęp
    0.08
     trouv
    0.08
    teness
    0.08
     aran
    0.08
     integer
    0.08
     lwe
    0.08
     znale
    0.07
     ઉપલબ્ધ
    0.07
    Activations Density 0.047%

    No Known Activations