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. 43066
    Prev
    Next
    INDEX
    Explanations

    motion

    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
    IFA
    -0.09
     factories
    -0.09
    }!
    -0.08
    יכול
    -0.08
    occup
    -0.08
    063
    -0.08
    ской
    -0.08
    ocup
    -0.08
    Ich
    -0.08
    Occup
    -0.08
    POSITIVE LOGITS
     consensus
    0.09
     प्रस्ताव
    0.08
    议
    0.08
     большин
    0.08
     обсуж
    0.08
     Suff
    0.08
     मत
    0.08
     विषय
    0.08
     disagreements
    0.08
     मतदान
    0.08
    Activations Density 0.012%

    No Known Activations