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. 19176
    Prev
    Next
    INDEX
    Explanations

    mathematical problems

    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
     pogosto
    -0.08
     és
    -0.08
     preguntas
    -0.08
     el
    -0.08
     �
    -0.07
     često
    -0.07
     अक्सर
    -0.07
     եւ
    -0.07
     impact
    -0.07
     doesn
    -0.07
    POSITIVE LOGITS
    ْم
    0.10
    ASHION
    0.10
    _"
    0.10
    !”
    0.10
    ْ
    0.09
    _'
    0.09
     anymore
    0.09
    !!!!
    0.09
    !!!!!
    0.09
     سوى
    0.09
    Activations Density 0.041%

    No Known Activations