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. 90053
    Prev
    Next
    INDEX
    Explanations

    ]

    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
     fos
    -0.08
     �
    -0.07
     mobiles
    -0.07
     bust
    -0.07
     ETF
    -0.07
     harness
    -0.07
     cellphone
    -0.07
     sns
    -0.07
     Discovery
    -0.07
     liberation
    -0.07
    POSITIVE LOGITS
    'école
    0.08
     بهترین
    0.08
    anges
    0.08
    inzwe
    0.08
    ociazione
    0.08
     веса
    0.08
    _WEIGHT
    0.07
     луч
    0.07
    richting
    0.07
    .weight
    0.07
    Activations Density 0.002%

    No Known Activations