© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68939
    Prev
    Next
    INDEX
    Explanations

    omorphic

    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
    室
    -0.08
    صد
    -0.08
     Babys
    -0.08
     babys
    -0.07
     Зав
    -0.07
     maternity
    -0.07
     صاحب
    -0.07
     Saud
    -0.07
     Erdogan
    -0.07
     Indic
    -0.07
    POSITIVE LOGITS
    sed
    0.08
    _axes
    0.08
    ouden
    0.08
    .For
    0.08
     புத
    0.08
     കഥാപാത്ര
    0.07
    RP
    0.07
     вред
    0.07
    ITION
    0.07
     nouveau
    0.07
    Activations Density 0.001%

    No Known Activations