© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95570
    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
    IZED
    -0.09
    jective
    -0.09
    ized
    -0.08
    phans
    -0.07
    ifers
    -0.07
     altında
    -0.07
    ſ
    -0.07
     bov
    -0.07
    ous
    -0.06
    াথে
    -0.06
    POSITIVE LOGITS
     nzira
    0.10
     الإجراءات
    0.10
    措施
    0.09
     إجراءات
    0.09
     estrategias
    0.09
     നടപട
    0.09
     procedures
    0.09
     prepara
    0.09
     estrategia
    0.09
     acciones
    0.09
    Activations Density 0.037%

    No Known Activations