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. 78705
    Prev
    Next
    INDEX
    Explanations

    deeper

    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
    ុក
    -0.09
    Vert
    -0.09
    .vert
    -0.09
     vert
    -0.08
    _vert
    -0.08
     hyp
    -0.08
    orio
    -0.08
    RIC
    -0.08
    eline
    -0.07
     isolated
    -0.07
    POSITIVE LOGITS
    เกี่ยว
    0.08
     Bere
    0.08
     MS
    0.08
     Formular
    0.08
     Magnetic
    0.08
     mengenai
    0.08
     delve
    0.07
     tentang
    0.07
     lanjut
    0.07
     Analyse
    0.07
    Activations Density 0.029%

    No Known Activations