© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 18322
    Prev
    Next
    INDEX
    Explanations

    "while" in other languages

    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
    .over
    -0.08
     =>
    -0.08
     which
    -0.08
     వంటి
    -0.08
    ,{↵
    -0.08
    లాంటి
    -0.08
    —a
    -0.07
     ўсіх
    -0.07
     ->
    -0.07
     Overall
    -0.07
    POSITIVE LOGITS
     tandis
    0.24
     whereas
    0.21
     mentre
    0.20
     enquanto
    0.20
     بينما
    0.20
     mientras
    0.19
     जबकि
    0.19
    ,而
    0.19
     جبکہ
    0.18
     while
    0.18
    Activations Density 0.138%

    No Known Activations