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. 15-RESID-POST-AA
    6. 19105
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .");
    -0.09
    어나
    -0.09
    ecer
    -0.08
     *>(
    -0.08
    "]).
    -0.08
    `).
    -0.08
    ']).
    -0.08
    printed
    -0.08
     nau
    -0.07
    adden
    -0.07
    POSITIVE LOGITS
    如下
    0.13
     şöyle
    0.13
     Here's
    0.12
    Here's
    0.11
     निम
    0.11
     voici
    0.11
     ఇలా
    0.11
     lautet
    0.11
     নিম
    0.11
     folgenden
    0.10
    Activations Density 0.048%

    No Known Activations