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. 43664
    Prev
    Next
    INDEX
    Explanations

    atmosphere

    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
     forts
    -0.08
    <Account
    -0.07
    (account
    -0.07
     contas
    -0.07
    本人
    -0.07
     payoff
    -0.07
     제출
    -0.07
    assigned
    -0.07
     cmds
    -0.07
     admiss
    -0.07
    POSITIVE LOGITS
    空气
    0.10
     gloom
    0.10
     Atmosphäre
    0.09
     sfeer
    0.09
     воздух
    0.09
     воздуха
    0.09
     angenehm
    0.09
     humidity
    0.09
     siente
    0.09
     haze
    0.09
    Activations Density 0.037%

    No Known Activations