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. 78517
    Prev
    Next
    INDEX
    Explanations

    |

    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
    tings
    -0.08
    ,到
    -0.07
    vary
    -0.07
     tangan
    -0.07
    Ct
    -0.07
     school
    -0.07
    _testing
    -0.07
    !'
    -0.07
     Sheet
    -0.07
    几年
    -0.07
    POSITIVE LOGITS
     beskr
    0.09
     أس
    0.09
    arkeun
    0.08
     umwe
    0.08
     כא
    0.08
     توض
    0.08
     שני
    0.08
     איבער
    0.08
     אוי�
    0.08
     опис
    0.08
    Activations Density 0.013%

    No Known Activations