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. 30641
    Prev
    Next
    INDEX
    Explanations

    water use

    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
     behave
    -0.09
     embrace
    -0.08
     obey
    -0.08
    _visit
    -0.08
     visit
    -0.07
     (*(
    -0.07
     Visit
    -0.07
     לג
    -0.07
     violate
    -0.07
     cherish
    -0.07
    POSITIVE LOGITS
     beslag
    0.09
    .Amount
    0.09
     Aufwand
    0.09
     sejumlah
    0.08
    iyya
    0.08
     hoeveelheid
    0.08
    _REQUIRED
    0.08
     огромное
    0.08
     талап
    0.08
     akeh
    0.08
    Activations Density 0.007%

    No Known Activations