© 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 EvalsExportsAPI 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. 49742
    Prev
    Next
    INDEX
    Explanations

    far

    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
     slightly
    -0.12
     حتی
    -0.11
     mucho
    -0.11
    Even
    -0.11
     Even
    -0.11
     Slight
    -0.11
     Much
    -0.10
    even
    -0.10
    _even
    -0.10
     थोड़ा
    -0.10
    POSITIVE LOGITS
     lik
    0.11
     большей
    0.10
     greater
    0.10
     groter
    0.10
    ชมป์
    0.10
     tin
    0.10
     превыш
    0.09
     nachdem
    0.09
     dead
    0.09
    भन्दा
    0.09
    Activations Density 0.018%

    No Known Activations