Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60961
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
    यों
    -0.08
    याँ
    -0.08
     rewarded
    -0.08
     Egy
    -0.08
     commonly
    -0.08
    illiseconds
    -0.08
    ,time
    -0.07
     Aos
    -0.07
    spolit
    -0.07
     بط
    -0.07
    POSITIVE LOGITS
    Jack
    0.09
    Bearer
    0.09
     jack
    0.09
    jack
    0.08
    bear
    0.08
     premier
    0.08
     premiere
    0.08
    CAS
    0.08
     Jack
    0.08
    Cas
    0.08
    Activations Density 2.071%

    No Known Activations