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. 43397
    Prev
    Next
    INDEX
    Explanations

    guard

    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
     �
    -0.08
    rama
    -0.08
     Hoop
    -0.08
    fam
    -0.07
     Cobb
    -0.07
    Lit
    -0.07
     orig
    -0.07
     jam
    -0.07
     Koe
    -0.07
    atm
    -0.07
    POSITIVE LOGITS
    rail
    0.08
     adm
    0.08
     вот
    0.07
    .G
    0.07
     Julius
    0.07
    措施
    0.07
     мест
    0.07
    Street
    0.07
    onz
    0.07
    คน
    0.07
    Activations Density 0.015%

    No Known Activations