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. 15-RESID-POST-AA
    6. 65
    Prev
    Next
    INDEX
    Explanations

    hostname

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    玩法
    -0.08
     kompat
    -0.08
     compatibility
    -0.08
    一种
    -0.08
     Compatibility
    -0.08
    ivalent
    -0.08
    Compat
    -0.08
     жан
    -0.08
    Compatibility
    -0.07
     분야
    -0.07
    POSITIVE LOGITS
    .hostname
    0.16
     hostname
    0.14
    hostname
    0.14
    _hostname
    0.14
    Hostname
    0.13
     VPN
    0.11
     Namen
    0.11
     localhost
    0.11
    names
    0.11
    namen
    0.10
    Activations Density 0.011%

    No Known Activations