© 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. 30267
    Prev
    Next
    INDEX
    Explanations

    achieve

    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
     Cruc
    -0.07
     gyr
    -0.07
    �
    -0.07
     Quart
    -0.07
     betray
    -0.07
    Quart
    -0.07
    lage
    -0.07
     fashioned
    -0.07
     Sack
    -0.07
    ders
    -0.07
    POSITIVE LOGITS
     feats
    0.08
    ment
    0.08
     attained
    0.08
     reproduc
    0.07
    itar
    0.07
    .sm
    0.07
     feat
    0.07
     ach
    0.07
     erzielt
    0.07
     convergence
    0.07
    Activations Density 0.026%

    No Known Activations