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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48303
    Prev
    Next
    INDEX
    Explanations

    Foreign languages and technical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surgical
    -0.09
     sikre
    -0.09
     sudo
    -0.09
     surgery
    -0.08
    synt
    -0.08
    sudo
    -0.08
     synthetic
    -0.08
     surat
    -0.08
     sicher
    -0.08
     sincerity
    -0.08
    POSITIVE LOGITS
    -songwriter
    0.18
    ftware
    0.12
    atchewan
    0.12
    utherland
    0.11
    writers
    0.11
     الذات
    0.11
    ittarius
    0.10
     Arabian
    0.10
    ariş
    0.10
    -faire
    0.10
    Activations Density 0.470%

    No Known Activations