Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11776
    Prev
    Next
    INDEX
    Explanations

    common English words

    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
     SON
    -0.08
     Lenn
    -0.08
     homogen
    -0.07
    .IM
    -0.07
     Sofa
    -0.07
     плать
    -0.07
     करनी
    -0.07
     dependent
    -0.07
     deterioration
    -0.07
     Dün
    -0.07
    POSITIVE LOGITS
     thriving
    0.10
     conseguem
    0.10
     thrive
    0.10
     thrives
    0.09
     mampu
    0.09
    ACTIVE
    0.09
     consegue
    0.09
    active
    0.09
    	active
    0.09
     способность
    0.09
    Activations Density 0.097%

    No Known Activations