© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94575
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     বর্তমানে
    -0.09
     હાલમાં
    -0.09
    ška
    -0.09
     momenteel
    -0.09
    ustes
    -0.09
     தற்போது
    -0.09
     wpis
    -0.09
    ғана
    -0.09
     Currently
    -0.08
    ortoq
    -0.08
    POSITIVE LOGITS
    父
    0.08
     parents
    0.08
    iblings
    0.08
     hangt
    0.08
     cameras
    0.08
     siblings
    0.08
     sibling
    0.08
     Türen
    0.08
     household
    0.08
    电视
    0.07
    Activations Density 0.090%

    No Known Activations