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. 98421
    Prev
    Next
    INDEX
    Explanations

    channels and mediums

    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
    olicies
    -0.08
     draaien
    -0.08
    理念
    -0.07
    思想
    -0.07
    stellungen
    -0.07
    .logic
    -0.07
    算法
    -0.07
     trabaho
    -0.07
     teori
    -0.07
     algorithms
    -0.07
    POSITIVE LOGITS
    渠道
    0.43
     channels
    0.40
     mediums
    0.37
     canales
    0.37
     channel
    0.36
     चैन
    0.35
     canais
    0.35
     medium
    0.35
     Channels
    0.35
    channels
    0.35
    Activations Density 0.232%

    No Known Activations