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. 109603
    Prev
    Next
    INDEX
    Explanations

    fart

    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
    roup
    -0.08
    ு�
    -0.08
     loans
    -0.08
    שה
    -0.07
    னி
    -0.07
     والق
    -0.07
    .loan
    -0.07
     Lus
    -0.07
    Loan
    -0.07
     tutoring
    -0.07
    POSITIVE LOGITS
    空气
    0.09
     loudly
    0.09
     Acoustic
    0.08
    _air
    0.08
    猛烈
    0.08
    屁
    0.08
     audible
    0.08
     воздуха
    0.08
    énom
    0.08
    omics
    0.08
    Activations Density 0.001%

    No Known Activations