© 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. 18673
    Prev
    Next
    INDEX
    Explanations

    letters and sounds

    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
     expressions
    -0.09
     homework
    -0.09
     хэмж
    -0.09
     велич
    -0.09
     мөр
    -0.09
    Expressions
    -0.09
    ahayag
    -0.09
     хэмжээ
    -0.08
    որը
    -0.08
    .Decimal
    -0.08
    POSITIVE LOGITS
     vowels
    0.15
     rearr
    0.14
     letters
    0.14
     vowel
    0.13
     conson
    0.12
     lettres
    0.12
     sonido
    0.12
     sonidos
    0.12
     letras
    0.12
     removing
    0.11
    Activations Density 0.022%

    No Known Activations