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. 12626
    Prev
    Next
    INDEX
    Explanations

    unlocks or achievements

    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
    _prices
    -0.09
    ovid
    -0.08
    干
    -0.08
     контакт
    -0.08
     Gelder
    -0.08
     Nachmittag
    -0.08
    Prices
    -0.08
    Kontakt
    -0.08
     prices
    -0.08
    Oval
    -0.08
    POSITIVE LOGITS
     milestone
    0.16
     milestones
    0.16
     achievements
    0.15
     অর্জ
    0.15
    -earned
    0.14
     accomplishments
    0.14
     achievement
    0.14
     earned
    0.13
    achievement
    0.13
     badge
    0.13
    Activations Density 0.071%

    No Known Activations