Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 56117
    Prev
    Next
    INDEX
    Explanations

    see, compare

    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
    ьем
    -0.09
    ’enfant
    -0.08
    寻
    -0.08
    'enfant
    -0.08
    Adress
    -0.08
    Quem
    -0.08
    _FIELD
    -0.08
    Founder
    -0.08
    builtin
    -0.08
    tọ
    -0.08
    POSITIVE LOGITS
    :i
    0.10
    :N
    0.08
    :D
    0.08
    :L
    0.08
    :w
    0.08
    :http
    0.08
    :list
    0.08
     Trim
    0.08
     nodded
    0.07
    :f
    0.07
    Activations Density 0.004%

    No Known Activations