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. 19648
    Prev
    Next
    INDEX
    Explanations

    salt

    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
    -0.07
     if
    -0.07
     dissemination
    -0.07
    ;"
    -0.07
     how
    -0.07
    	if
    -0.07
     Bitmap
    -0.06
     Mode
    -0.06
    engo
    -0.06
     observed
    -0.06
    POSITIVE LOGITS
     ქ
    0.10
     һес
    0.10
    итидә
    0.10
     خالد
    0.09
     wagtda
    0.09
     болиду
    0.09
     tlhela
    0.09
    қид
    0.09
    итигә
    0.09
     кәл
    0.09
    Activations Density 0.003%

    No Known Activations