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. 113858
    Prev
    Next
    INDEX
    Explanations

    ServiceNow Glide elements

    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
    cloak
    -0.08
     plek
    -0.08
    国外
    -0.07
    �
    -0.07
     ewe
    -0.07
     że
    -0.07
    隔
    -0.07
    MITTED
    -0.07
     inbound
    -0.07
     contiguous
    -0.07
    POSITIVE LOGITS
    ('[
    0.08
     оцен
    0.08
    ("[
    0.08
    communications
    0.08
    .push
    0.08
    _led
    0.08
     tve
    0.07
    _fs
    0.07
    _display
    0.07
    .evaluate
    0.07
    Activations Density 0.002%

    No Known Activations