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. 60601
    Prev
    Next
    INDEX
    Explanations

    Conditional statements in code

    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
    @m
    -0.08
     kolem
    -0.08
     sandy
    -0.08
    \S
    -0.08
     ök
    -0.08
     Mez
    -0.07
     sow
    -0.07
     süd
    -0.07
     Sandy
    -0.07
    north
    -0.07
    POSITIVE LOGITS
    Fallback
    0.13
     fallback
    0.12
    fallback
    0.11
    allback
    0.10
     альтернатив
    0.09
     conditional
    0.08
     alternatives
    0.08
    Conditional
    0.08
    conditional
    0.08
     переключ
    0.08
    Activations Density 0.011%

    No Known Activations