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. 3-RESID-POST-AA
    6. 12627
    Prev
    Next
    INDEX
    Explanations

    systems and abstract concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     troubled
    -0.08
     వారికి
    -0.07
     dob
    -0.07
     ਰਹ
    -0.07
     God
    -0.07
    dob
    -0.07
    (scanner
    -0.07
    Remain
    -0.07
    .ini
    -0.07
    /ph
    -0.07
    POSITIVE LOGITS
     Paj
    0.10
     Π
    0.08
    ött
    0.08
    _ws
    0.08
     sheath
    0.07
     mj
    0.07
    askar
    0.07
    ère
    0.07
     jets
    0.07
    kü
    0.07
    Activations Density 0.000%

    No Known Activations