© 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. 19-RESID-POST-AA
    11. 102136
    Prev
    Next
    INDEX
    Explanations

    sentence

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddefnyddio
    -0.09
    жди
    -0.09
    'utiliser
    -0.08
     umuk
    -0.08
     fòr
    -0.08
     geschikte
    -0.08
     utiliser
    -0.08
    ’utiliser
    -0.08
     typename
    -0.08
     ubiquit
    -0.08
    POSITIVE LOGITS
     sentence
    0.17
     "...
    0.15
     paragraph
    0.15
    _sentence
    0.15
     sentences
    0.14
     continues
    0.14
    Sentence
    0.14
    paragraph
    0.14
     جمله
    0.14
    sentence
    0.13
    Activations Density 0.039%

    No Known Activations