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. 111743
    Prev
    Next
    INDEX
    Explanations

    Yemen

    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
    -NLS
    -0.09
    似
    -0.08
     registering
    -0.07
     Renting
    -0.07
     renting
    -0.07
     conveys
    -0.07
    -Max
    -0.07
     prere
    -0.07
     Measure
    -0.07
     Fu
    -0.07
    POSITIVE LOGITS
     اليمن
    0.09
     Yemen
    0.09
    _trim
    0.08
     coron
    0.08
    �
    0.08
     ayam
    0.08
     Coronavirus
    0.08
     Cisco
    0.08
     spacecraft
    0.08
     Arabian
    0.08
    Activations Density 0.002%

    No Known Activations