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. 43407
    Prev
    Next
    INDEX
    Explanations

    neuro

    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
     Configure
    -0.10
     mentality
    -0.08
    /libs
    -0.07
     Reck
    -0.07
    nya
    -0.07
     wars
    -0.07
     heir
    -0.07
     escalating
    -0.07
    -0.07
     revenues
    -0.07
    POSITIVE LOGITS
     пов
    0.07
    -hole
    0.07
    秘
    0.07
     supr
    0.07
    ornal
    0.07
    0.07
    isi
    0.07
    comed
    0.07
     retina
    0.06
     juríd
    0.06
    Activations Density 0.009%

    No Known Activations