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. 44829
    Prev
    Next
    INDEX
    Explanations

    commercial

    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
    anı
    -0.10
    960
    -0.07
     coi
    -0.07
     düşünü
    -0.07
     Fort
    -0.07
    'ın
    -0.07
     geliyor
    -0.07
     mgb
    -0.07
     ase
    -0.07
    Dirty
    -0.07
    POSITIVE LOGITS
    铺
    0.10
    interp
    0.08
     tensions
    0.08
     tension
    0.08
     raí
    0.08
     vorgesch
    0.08
    shade
    0.08
     rassemble
    0.08
     এমন
    0.08
    ATEG
    0.08
    Activations Density 0.002%

    No Known Activations