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. 78508
    Prev
    Next
    INDEX
    Explanations

    t

    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
     außer
    -0.08
    ేవ
    -0.08
    iefer
    -0.07
     frü
    -0.07
     Herkunft
    -0.07
     után
    -0.07
     optimal
    -0.07
     стро
    -0.07
     Philly
    -0.07
    	se
    -0.07
    POSITIVE LOGITS
    Master
    0.09
    -master
    0.09
    _MASTER
    0.08
    leis
    0.08
     MASTER
    0.08
    件
    0.08
    pra
    0.08
    Flo
    0.07
    lub
    0.07
    _master
    0.07
    Activations Density 0.002%

    No Known Activations