© 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. 23-RESID-POST-AA
    11. 51159
    Prev
    Next
    INDEX
    Explanations

    you

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desires
    -0.13
     requires
    -0.12
     요구
    -0.12
     requer
    -0.12
     zaht
    -0.11
    .des
    -0.11
     vereist
    -0.11
     demands
    -0.11
    要求
    -0.11
     exige
    -0.11
    POSITIVE LOGITS
    ’d
    0.16
     need
    0.15
     gostaria
    0.13
     want
    0.13
    'aimerais
    0.13
     wondered
    0.11
    ’re
    0.11
     have
    0.10
     chcia
    0.10
     perlu
    0.10
    Activations Density 0.036%

    No Known Activations