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. 112829
    Prev
    Next
    INDEX
    Explanations

    hoping

    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
    axs
    -0.08
     auditor
    -0.07
    ADC
    -0.07
     ADC
    -0.07
     Agricultural
    -0.07
    .li
    -0.07
    خش
    -0.07
     NAC
    -0.07
    Outgoing
    -0.07
     ناخ
    -0.07
    POSITIVE LOGITS
    …..
    0.09
     redis
    0.09
     neman
    0.08
    ……”
    0.08
     __(
    0.07
    ……”↵↵
    0.07
    ……
    0.07
    рани
    0.07
    :”
    0.07
    été
    0.07
    Activations Density 0.009%

    No Known Activations