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. 12823
    Prev
    Next
    INDEX
    Explanations

    words ending in "ing"

    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
    λού
    -0.08
     svega
    -0.08
     vóór
    -0.08
    భ
    -0.08
     большинстве
    -0.08
     omoguć
    -0.08
     կրթ
    -0.08
     والس
    -0.08
     које
    -0.07
     vooruit
    -0.07
    POSITIVE LOGITS
    正在
    0.09
    ುತ್ತಿರುವ
    0.09
     sebuah
    0.08
     :::::
    0.08
    _icon
    0.07
    .parameters
    0.07
     unsuccess
    0.07
    _example
    0.07
    Transfer
    0.07
    _tuple
    0.07
    Activations Density 0.118%

    No Known Activations