Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19490
    Prev
    Next
    INDEX
    Explanations

    necessary, appropriate (foreign)

    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
     Isn't
    -0.08
     naquela
    -0.08
    -0.07
     isn't
    -0.07
    (notification
    -0.07
    [msg
    -0.07
     affirmation
    -0.07
     can't
    -0.07
     ใน
    -0.07
    之一
    -0.07
    POSITIVE LOGITS
     gerekli
    0.11
     необходимых
    0.10
     uygun
    0.10
     gült
    0.09
    :↵↵
    0.09
     geeign
    0.09
     appropriate
    0.09
     необходимые
    0.09
     usable
    0.09
     necessary
    0.09
    Activations Density 0.024%

    No Known Activations