© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 97554
    Prev
    Next
    INDEX
    Explanations

    cuchar

    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
    �
    -0.08
     mourn
    -0.08
     präsent
    -0.07
     Voir
    -0.07
     mgbe
    -0.07
     stort
    -0.07
     opslag
    -0.07
     mensagens
    -0.07
     BAND
    -0.07
     þegar
    -0.07
    POSITIVE LOGITS
     adobe
    0.09
    ara
    0.08
     rigtig
    0.08
    adı
    0.08
    ad
    0.08
    Thumb
    0.08
    _perm
    0.08
    ಿಯಿಂದ
    0.08
     permiso
    0.08
    adzira
    0.08
    Activations Density 0.001%

    No Known Activations