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. 19416
    Prev
    Next
    INDEX
    Explanations

    counting

    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
     PARTICULAR
    -0.08
    ики
    -0.08
    ик
    -0.08
     өзінің
    -0.08
     Larsen
    -0.07
    mittelt
    -0.07
    ындағы
    -0.07
     particular
    -0.07
    ينة
    -0.07
    ýan
    -0.07
    POSITIVE LOGITS
     count
    0.23
    Count
    0.22
    _count
    0.22
    数量
    0.20
     Count
    0.19
     Anzahl
    0.19
    _COUNT
    0.19
     саны
    0.18
     എണ്ണം
    0.18
     количество
    0.18
    Activations Density 0.068%

    No Known Activations