© 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. 51200
    Prev
    Next
    INDEX
    Explanations

    strict

    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
     recomendable
    -0.08
    �
    -0.08
     facilité
    -0.08
    ബ്
    -0.08
    atz
    -0.07
     preferable
    -0.07
    ekom
    -0.07
     genügend
    -0.07
    alom
    -0.07
     encouraged
    -0.07
    POSITIVE LOGITS
     stringent
    0.45
     strict
    0.41
    严格
    0.41
     কঠ
    0.38
     строг
    0.38
     कठ
    0.38
     stric
    0.36
    严
    0.34
     estrict
    0.33
     rigorous
    0.33
    Activations Density 0.055%

    No Known Activations