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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98492
    Prev
    Next
    INDEX
    Explanations

    ол

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.09
    і
    -0.09
    iði
    -0.08
    .E
    -0.08
     ama
    -0.08
     geç
    -0.08
     Ge
    -0.08
    �
    -0.08
    ્તિ
    -0.08
    、不
    -0.08
    POSITIVE LOGITS
     edits
    0.09
    rop
    0.08
    ബി
    0.08
    .s
    0.08
    േറ്റ
    0.08
    VS
    0.07
    65
    0.07
    het
    0.07
    gus
    0.07
    ielsen
    0.07
    Activations Density 0.000%

    No Known Activations