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

    Neuronpedia

    APICircuit 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. 11977
    Prev
    Next
    INDEX
    Explanations

    targeted

    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
     lega
    -0.08
    leben
    -0.07
     Gide
    -0.07
    tray
    -0.07
     rough
    -0.07
    479
    -0.07
     refr
    -0.07
     Fig
    -0.07
     controvers
    -0.07
     tekan
    -0.07
    POSITIVE LOGITS
    -target
    0.09
     cibl
    0.09
     targeting
    0.09
    maßnahmen
    0.09
    针对
    0.09
    Sms
    0.09
    _campaign
    0.08
     honing
    0.08
    -aware
    0.08
    ely
    0.08
    Activations Density 0.011%

    No Known Activations