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. 43818
    Prev
    Next
    INDEX
    Explanations

    code commands

    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
    possibly
    -0.09
    achar
    -0.08
    .Bot
    -0.08
    	attr
    -0.08
     Campeonato
    -0.07
     名前
    -0.07
    attr
    -0.07
     Treatment
    -0.07
     possibly
    -0.07
    Attr
    -0.07
    POSITIVE LOGITS
    顺
    0.08
     civ
    0.07
     تیار
    0.07
    放心
    0.07
    ைகள
    0.07
    综合
    0.07
     সম
    0.07
    -round
    0.07
    融资
    0.07
     தன
    0.07
    Activations Density 0.002%

    No Known Activations