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. 76305
    Prev
    Next
    INDEX
    Explanations

    Sentence endings/quotations marks

    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
     thuận
    -0.09
     corrobor
    -0.09
     tuk
    -0.08
     निर्�
    -0.08
     году
    -0.08
     Studios
    -0.08
     ਡ
    -0.08
     économ
    -0.07
    .Getter
    -0.07
     распредел
    -0.07
    POSITIVE LOGITS
    Give
    0.08
    ORG
    0.08
    allos
    0.07
    CNN
    0.07
    Zap
    0.07
     bağ
    0.07
     ursprünglich
    0.07
     oda
    0.07
     Aya
    0.07
     Carlisle
    0.07
    Activations Density 0.053%

    No Known Activations