© 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. 51698
    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
     becomes
    -0.14
     deviennent
    -0.12
     devient
    -0.11
     aprende
    -0.11
     ficam
    -0.11
     يصبح
    -0.10
     develops
    -0.10
     chega
    -0.10
     evolves
    -0.10
    expand
    -0.10
    POSITIVE LOGITS
     received
    0.17
     bought
    0.16
     stumbled
    0.15
     purchased
    0.15
     took
    0.15
     died
    0.14
     failed
    0.14
     reached
    0.14
     сделали
    0.14
     contributed
    0.14
    Activations Density 0.168%

    No Known Activations