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. 130963
    Prev
    Next
    INDEX
    Explanations

    walls and wall materials

    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
     foundation
    -0.08
     contracts
    -0.08
     pond
    -0.08
     pen
    -0.08
     Vertrag
    -0.08
     oit
    -0.08
     crust
    -0.07
     kezd
    -0.07
     filtration
    -0.07
     pö
    -0.07
    POSITIVE LOGITS
     Gy
    0.10
    Gy
    0.10
     Partition
    0.09
    gy
    0.09
    Partition
    0.09
    Block
    0.09
     partition
    0.09
    _partition
    0.09
     hollow
    0.08
     Mont
    0.08
    Activations Density 0.004%

    No Known Activations