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. 91051
    Prev
    Next
    INDEX
    Explanations

    thousands

    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
     Fre
    -0.09
     ged
    -0.08
    媒
    -0.08
    serialized
    -0.08
     nk
    -0.08
    앤
    -0.08
     Hub
    -0.08
    集中
    -0.07
    동
    -0.07
    แบ่ง
    -0.07
    POSITIVE LOGITS
    _src
    0.09
     સ્ત
    0.08
     vowel
    0.08
     digits
    0.08
    (src
    0.08
     cartridge
    0.08
     vocht
    0.08
    /root
    0.08
     tum
    0.08
    .Context
    0.07
    Activations Density 0.008%

    No Known Activations