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. 30813
    Prev
    Next
    INDEX
    Explanations

    "two" or "both"

    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
    mith
    -0.09
    نا
    -0.08
    য
    -0.08
    状
    -0.08
    _Widget
    -0.07
                    
    -0.07
     etwas
    -0.07
     cafeter
    -0.07
     আল
    -0.07
    ঙ্ক
    -0.07
    POSITIVE LOGITS
     Releases
    0.08
     高频
    0.08
     Consultancy
    0.08
     Familia
    0.07
     eagle
    0.07
    vun
    0.07
     Plane
    0.07
    family
    0.07
     Mascul
    0.07
     Mortgage
    0.07
    Activations Density 0.135%

    No Known Activations