© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18560
    Prev
    Next
    INDEX
    Explanations

    为

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vertheless
    -0.09
     దీన
    -0.09
    ․․
    -0.08
     selben
    -0.08
    داع
    -0.08
    hew
    -0.08
     purported
    -0.08
     precar
    -0.08
    possible
    -0.07
     цього
    -0.07
    POSITIVE LOGITS
     силы
    0.12
     शक्ति
    0.12
    动力
    0.12
    力量
    0.11
     ताक
    0.11
     قوة
    0.11
     القوة
    0.10
     शक्त
    0.10
     القدرة
    0.10
     nguvu
    0.10
    Activations Density 0.003%

    No Known Activations