Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12276
    Prev
    Next
    INDEX
    Explanations

    in

    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
    enka
    -0.08
    Profiles
    -0.08
     Profiles
    -0.08
     Srbije
    -0.07
    ssue
    -0.07
     Profil
    -0.07
     sam
    -0.07
     profil
    -0.07
    ella
    -0.07
    ellingen
    -0.07
    POSITIVE LOGITS
     larg
    0.08
     bạc
    0.08
     aje
    0.08
     emboss
    0.07
     род
    0.07
    ઢ
    0.07
     отриц
    0.07
     Joseph
    0.07
     extracting
    0.07
     larga
    0.07
    Activations Density 0.000%

    No Known Activations