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. 11588
    Prev
    Next
    INDEX
    Explanations

    a

    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
    ]))
    -0.09
    ])),
    -0.08
    _results
    -0.08
     resalt
    -0.08
     actuaciones
    -0.08
    icipants
    -0.08
    ajat
    -0.08
    leit
    -0.08
    利益
    -0.08
    ]),
    -0.08
    POSITIVE LOGITS
     осво
    0.10
     hobby
    0.10
    教程
    0.09
     beginners
    0.09
     חדשה
    0.09
     beginner
    0.09
     compétence
    0.09
    Curso
    0.09
     vreemde
    0.08
     Anfänger
    0.08
    Activations Density 0.034%

    No Known Activations